Long Short-Term Memory (LSTM)

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

• Medium-term memoryconcept0.756
  Vascular clamp's function: holding specific predictions stable over timescales longer than working memory.
• Large Language Models (LLMs)concept0.734
  Transformer-based models like GPT-4, LaMDA, PaLM; assessed for GWT indicators.
• LLM Meta-Cognitionconcept0.730
  The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
• LLM Introspective Self-Reportconcept0.729
  The capacity of Kimi K2.5 to evaluate its own internal emotional state when steered, used as a novel interpretability signal
• LLM Self-Correctionconcept0.725
  Related capability where LLMs correct their own outputs, studied via linear representations.
• LLM psychosisconcept0.724
  Tendency for models to get lost in roleplay or doom spirals, mitigated by expanded awareness.
• LLM-Judge Data Attributionmethod0.722
  Alternative data attribution approach using an LLM as a judge; compared against the probe-based method.
• Linear mixed-effects models (LMMs)method0.719
  Primary statistical model with random intercept by conversation, REML estimation, for pooled conversation-turn observations