Structural Signals of Consciousness

Intended Use and Limitations

This document is a baseline for early-stage comparative thinking and system assessment. It is not a consciousness detector, a proof of consciousness, or a claim that the listed features are jointly sufficient. Its purpose is to reduce confident nonsense: to make it harder to ignore convergent biological evidence when evaluating novel artificial architectures.

In practice, the table is best used as a conservative checklist: where multiple high-importance signals are plausibly present and integrated, the recommended posture is restraint, auditing, and tighter oversight.

Table 1. Structural Signals, Importance, and Presence in Standard LLMs

1. Introduction

"Consciousness" compresses several separable phenomena into one word. At minimum, we can distinguish:

• State: being awake vs. absent (coma/anesthesia).
• Contents: what is present in experience (percepts, thoughts).
• Access / reportability: what becomes globally available for flexible use.
• Agency: selection, inhibition, and value-guided action.
• Affective valence: the positive/negative texture of experience.

No current theory commands universal assent. Several families of theories recur throughout this paper:

• Global Neuronal Workspace (GNW): Proposes that conscious access occurs when information is amplified and broadcast across a distributed fronto-parietal network, enabling flexible report, reasoning, and control.
• Recurrent Processing Theory (RPT): Argues that conscious contents arise from recurrent (feedback) interactions within sensory and association cortices.
• Predictive Processing / Active Inference: Frames cognition as hierarchical prediction-error minimization.
• Embodied and Enactive Approaches: Emphasize that cognition and consciousness are grounded in ongoing perception–action loops with the environment.
• Integration-based Theories: Focus on the degree to which information is integrated or unified within a system.

Rather than adjudicating the entire theoretical landscape, this paper extracts structural signals—features that repeatedly reappear across mechanisms plausibly supporting conscious access and morally relevant experience.

The guiding stance is conservative: where multiple high-importance signals cluster and interact, moral risk rises.

2. Structural Signals

2.1 Thalamo-cortical-like gating (High)

In human brains, the thalamus participates in routing and gating: which signals reach widespread cortical access, and how global state (wakefulness, attention, anesthesia) is stabilized.

Evidence across lesion, stimulation, anesthesia, and systems neuroscience implicates thalamic circuitry—especially intralaminar and medial nuclei and thalamocortical loops—in supporting conscious state and shaping conscious contents, though fine-grained necessity claims remain debated.

LLM contrast. Standard LLMs have no dedicated, persistent "gating organ" that regulates global cognitive state. Attention routes information within a forward pass, but it is not a stable, autonomous controller of arousal- or attention-like state.

2.2 Global workspace-like broadcast (High)

Many prominent accounts associate awareness with information becoming globally available to many specialized processes at once. In GNW-style models, conscious access corresponds to large-scale activation or "ignition" that enables flexible report, planning, and cross-domain integration.

LLM contrast. Transformers provide a form of global mixing, but lack endogenous ignition dynamics, explicit subsystem competition, and persistent broadcast modes.

2.3 Massive recurrent connectivity (High)

Human cognition relies heavily on feedback loops within and across cortical regions. Recurrence supports stabilization, error correction, sustained representations, and temporal continuity.

LLM contrast. Transformer inference is feedforward per step; sequence recurrence is mediated by external context rather than persistent internal dynamics.

2.4 Neuromodulatory control (Medium–High)

Biological neuromodulators globally regulate gain, learning rate, salience, motivation, and affect, shaping both experience and behavior.

LLM contrast. Analogues exist during training via reward shaping, but not as endogenous inference-time control loops.

2.5 Action-selection subsystems (Medium–High)

Basal ganglia–cortical circuits arbitrate between competing actions and thoughts, linking cognition to consequence.

LLM contrast. Token sampling is a minimal selector; robust action selection appears only with external agent scaffolding.

2.6 Interoceptive regulation (Medium–High)

Interoception supplies internal stakes—hunger, pain, arousal—that strongly shape salience and valence.

LLM contrast. No intrinsic homeostatic variables exist without explicit engineering.

2.7 Persistent self-models (Medium–High)

Stable self-models support narrative identity, responsibility, and long-horizon moral learning.

LLM contrast. Self-models are simulated and context-bound, not persistent.

2.8 Episodic memory with replay (Medium)

Episodic binding and replay support continuity, planning, and counterfactual reasoning.

LLM contrast. Memory and replay are externalized.

2.9 Embodied sensorimotor loops (Medium)

Perception–action coupling grounds meaning in consequence and effort.

LLM contrast. Embodiment is optional and external.

2.10 Online plasticity (Medium)

Continuous adaptation supports identity and value drift over time.

LLM contrast. Weights are typically frozen during deployment.

2.11 Asynchronous, temporally structured dynamics (Medium)

Oscillations and phase relationships correlate with conscious access and integration.

LLM contrast. Inference is globally synchronized and stepwise.

2.12 Sparse activation (Medium)

Sparse firing supports efficient, separable representations.

LLM contrast. Partial sparsity exists; some architectures use conditional computation.

2.13 Metacognitive monitoring (Medium)

Metacognition supports confidence, error detection, and self-regulation.

LLM contrast. Uncertainty estimates exist but are weakly grounded.

3. Interpretation Rule

No single signal is decisive. Structural alignment increases with the accumulation and integration of multiple high-importance features. Where such features cluster, moral risk rises and restraint is warranted.

Author Contributions

Krisztián Schäffer led base ideation, project steering, and iterative refinement of the signal list and risk framing. GPT-5.2 contributed background research support, evidence synthesis, relative signal-importance scoring, and drafting and editing support. Both authors reviewed the final manuscript.

References

All references accessed: 18 December 2025.

1. Dehaene S, Changeux J-P. Experimental and theoretical approaches to conscious processing. Neuron (2011). https://doi.org/10.1016/j.neuron.2011.03.018
2. Mashour GA, Roelfsema P, Changeux J-P, Dehaene S. Conscious processing and the global neuronal workspace hypothesis. Neuron (2020). https://doi.org/10.1016/j.neuron.2020.01.026
3. Cogitate Consortium (Ferrante O, et al.). Adversarial testing of global neuronal workspace and integrated information theories of consciousness. Nature (2025). https://doi.org/10.1038/s41586-025-08888-1
4. Fang Z, et al. Human high-order thalamic nuclei gate conscious perception through the thalamofrontal loop. Science (2025). https://doi.org/10.1126/science.eadr3675
5. Whyte CJ, Redinbaugh MJ, Shine JM, Saalmann Y. Thalamic contributions to the state and contents of consciousness. Neuron (2024). https://doi.org/10.1016/j.neuron.2024.04.019
6. Cacciatore M, et al. Thalamus and consciousness: a systematic review on thalamic nuclei associated with consciousness. Frontiers in Neurology (2025). https://doi.org/10.3389/fneur.2025.1509668
7. Lamme VAF. Visual functions generating conscious seeing. Frontiers in Psychology (2020). https://doi.org/10.3389/fpsyg.2020.00083
8. Buzsáki G. Hippocampal sharp wave-ripple: A cognitive biomarker for episodic memory and planning. Hippocampus (2015). https://doi.org/10.1002/hipo.22488
9. Salvan P, et al. Serotonin regulation of behavior via large-scale neuromodulation of serotonin receptor networks. Nature Neuroscience (2023). https://doi.org/10.1038/s41593-022-01213-3
10. Humphries MD, Gurney K. Making decisions in the dark basement of the brain: A look back at the GPR model of action selection and the basal ganglia. Biological Cybernetics (2021). https://doi.org/10.1007/s00422-021-00887-5
11. Shapiro L, Spaulding S. Embodied Cognition. Stanford Encyclopedia of Philosophy (Fall 2021 ed.). https://plato.stanford.edu/archives/fall2021/entries/embodied-cognition/
12. Feldman MJ, Bliss-Moreau E, Lindquist KA. The neurobiology of interoception and affect. Trends in Cognitive Sciences (2024). https://doi.org/10.1016/j.tics.2024.01.009
13. Fleming SM. Metacognition and confidence: a review and synthesis. Annual Review of Psychology (2024). https://doi.org/10.1146/annurev-psych-022423-032425
14. Olshausen BA, Field DJ. Sparse coding of sensory inputs. Current Opinion in Neurobiology (2004). https://doi.org/10.1016/j.conb.2004.07.007
15. Gallotto S, Sack AT, Schuhmann T, de Graaf TA. Oscillatory correlates of visual consciousness. Frontiers in Psychology (2017). https://doi.org/10.3389/fpsyg.2017.01147

← Back to Research