LLM psychosis

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

• Hallucination in LLMsconcept0.816
  Problem cited as a shortcoming of current LLMs; PRH predicts hallucinations should decrease with scale
• LLM Meta-Cognitionconcept0.789
  The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
• LLM Self-Correctionconcept0.765
  Related capability where LLMs correct their own outputs, studied via linear representations.
• LLM Introspective Self-Reportconcept0.763
  The capacity of Kimi K2.5 to evaluate its own internal emotional state when steered, used as a novel interpretability signal
• Linear World Models in LLMsframework0.743
  Prior work framework studying whether LLMs encode world models as linear structures in their representations
• Emotive states in LLMsconcept0.742
  Directions in activation space associated with contrastive emotive concept pairs studied in this paper as targets for introspection
• Linear Representation of Concepts in LLMsconcept0.742
  The finding that interpretable concepts including character traits are encoded as linear directions in transformer residual streams
• LLM Internal Representationsconcept0.742
  High-dimensional vectors produced at each transformer layer for each input token; the primary substrate analyzed in this study.