Transformer architecture permits introspection; saying LLMs cannot introspect on past internal states is wrong.

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

• 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.quote0.874
  Core summary of Janus' position on autoregressive recurrence enabling introspection.
• 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.quote0.865
  Core quote asserting architectural introspection permission.
• LLM introspection on internal computations is architecturally permitted; whether models leverage this is an empirical question.claim0.830
  Core claim directly challenged by prior work denying introspection; forms foundation for Koan Battery introspection studies.
• Do LLMs leverage architectural capacity for introspection on internal computations and prior token generation?question0.829
  Central empirical question separating architectural possibility from actual model behavior; gates introspection research.
• Different introspective tasks may preferentially use different path distributions in the transformer.claim0.807
  Interpretive claim connecting exponential path combinatorics to Lindsey's layer-dependent findings.
• LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenonclaim0.797
  Primary positive claim of the paper, grounded in strength comparison and localization results
• "Our findings demonstrate that LLMs can compute meaningful functions over perturbations to their internal states, establishing introspection as a real but layer-dependent phenomenon that merits further investigation."quote0.790
  Central thesis statement of the paper
• Current LLMs cannot faithfully represent transformative experiences with epistemically opaque outcomes.claim0.785