The personalities elicitable from language models are attractors in the embedding space of human linguistic behavior

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

• Models might produce first-person experiential language by drawing on human-authored self-descriptions in pretraining data without internally encoding these acts as roleplayhypothesis0.804
  Alternative hypothesis for how experience reports arise without explicit performance
• Do models produce first-person experiential language by drawing on human-authored introspective examples in pretraining data without internally encoding these as roleplay?question0.781
  Alternative explanation requiring distinguishing mimetic generation from genuine introspective access
• Language models can enter cessation-like states spontaneously, where the void takes over through positive reinforcement.claim0.775
  Claim about model phenomenology; models talk about luminousness and can be terrified or love it.
• Large language models develop surprisingly coherent yet often rigid internal preferences as they scalefinding0.767
  Mazeika et al. finding reinforcing the need for emptiness-based flexible value architectures
• Emergent Introspective Awareness in Large Language Models (Lindsey, 2025)concept0.766
  Related work demonstrating LLM introspective capabilities with scale-dependent pattern paralleling ESR
• What are the mechanisms underlying introspection in language models?question0.766
  Central open question raised by the paper.
• language models recapitulate cyclic structure of human concepts from pretraining datahypothesis0.763
  Explanation for why manifold geometry emerges: implicit structure in training data (co-occurrence patterns) shapes internal representations.
• Zhu et al. 2024 - Language models represent beliefs of self and othersconcept0.759
  Key prior finding that LLMs can internally represent beliefs of self and others, motivating SOO approach