internal states of agent

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

• internal emotional stateconcept0.791
  The possibility of a stably encoded, causally active emotional state within LLMs, as distinct from token-by-token semantic content
• Intentional Control of Internal Statesfinding0.774
  Models can modulate their internal representations when instructed or incentivized to 'think about' a concept; effect replicates across all tested models regardless of capability.
• Thoughts As Agentsconcept0.755
  Core assertion extending William James: thoughts are not passive but active agents that facilitate their own transformation and remapping in cognitive systems.
• Stateful Internal Representationconcept0.745
  A representation that maintains stable activation across many tokens rather than being locally triggered by specific content
• Internal states appear to encode Bayesian beliefs about hidden external states.claim0.745
  The inferential interpretation of internal dynamics.
• Agentconcept0.739
  Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
• Internal Featuresconcept0.729
  Representations inside LLMs that can be intervened upon.
• Internal uncertaintyconcept0.720
  The model's internal representation of uncertainty hypothesized to trigger self-reflection