LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenon

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

• LLM introspection on internal computations is architecturally permitted; whether models leverage this is an empirical question.claim0.834
  Core claim directly challenged by prior work denying introspection; forms foundation for Koan Battery introspection studies.
• Saying that LLMs cannot introspect or cannot introspect on what they were doing internally while generating or reading past tokens in principle is just dead wrong. The architecture permits it.quote0.827
  Core quote asserting architectural introspection permission.
• So at any point in the network, the transformer not only receives information from its past... but also has causal influence over its future processing. So, saying that LLMs cannot introspect... is incorrect.quote0.821
  Core summary of Janus' position on autoregressive recurrence enabling introspection.
• LLM representations exhibit intriguing patterns under spatio-permutational analyses, suggesting a potentially profound yet tentative indication of consciousness.claim0.821
  Qualified positive claim from spatio permutation analysis where two cases satisfy all three criteria.
• The systematic behavioral shift of LLMs under self-referential processing conditions predicted by consciousness theories represents something more structured than superficial correlations in training dataclaim0.820
  The paper's claim that theoretical convergence across GWT, RPT, HOT, IIT makes the findings non-coincidental
• Do LLMs leverage architectural capacity for introspection on internal computations and prior token generation?question0.816
  Central empirical question separating architectural possibility from actual model behavior; gates introspection research.
• If self-referential processing causally instantiates recurrent integration, global broadcasting, and metacognitive monitoring at the algorithmic level, then LLMs under this regime would satisfy the functional requirements of leading consciousness theorieshypothesis0.813
  The paper's key theoretical prediction that mechanistic studies should investigate
• We hypothesize that 'consciousness' phenomena can be observed in the internal states of an LLM, specifically in its learned representations when analyzed as a sequence.hypothesis0.812
  Primary research hypothesis driving the entire study; operationalized via three criteria.