Functional and phenomenal introspection are distinguishable, and whether they correlate in machines is an open question.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• The paper does not claim these models have conscious felt experience; introspection is defined operationally as causal informational coupling agnostic about consciousnessclaim0.837
  Explicit scope limitation following Comsa & Shanahan 2025 and McClelland 2024
• Introspection relies on general-purpose computational mechanisms—attention-based anomaly detection and residual stream dynamics—rather than specialized introspection circuitsclaim0.821
  Interpretive claim about the mechanistic substrate of introspection in LLMs
• If someone develops clear enough introspection, they will eventually conclude that thought is rendered as subtle perturbations in phenomenal fields.hypothesis0.817
  Cube Flipper's prediction about convergence of insight practice on field model.
• The functionalist denies the coherence of philosophical zombies: experience, insofar as it has any determinable character, is itself a functional propertyclaim0.806
  Core argument against essentialism: there is no property of consciousness over and above its functional manifestations
• LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenonclaim0.806
  Primary positive claim of the paper, grounded in strength comparison and localization results
• Functional introspective awareness enables interpretability and reasoning about decisionsclaim0.804
  Grounded responses to reasoning questions could improve transparency; speculatively might facilitate deception; significance grows if capability becomes more reliable.
• Our results demonstrate that modern language models possess at least a limited, functional form of introspective awareness.quote0.804
  Abstract's main conclusion.
• Do apparent introspection results reflect genuine metacognitive access to internal representations, or do they emerge from simpler mechanisms such as output distribution shifts?question0.803
  Key discriminating question motivating the baseline control experiment