Self-Similarity

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

• Self-Other Overlapconcept0.817
  The extent to which a model exhibits similar internal representations when reasoning about itself and others in similar contexts
• Self-reflectionconcept0.816
  The ability of reasoning LLMs to review and revise previous reasoning steps during inference
• Self-Referenceconcept0.812
  Central phenomenon of the paper: systems that refer to themselves in ways problematic for conventional logic but constitutive of life.
• Selfingconcept0.810
  Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
• Self-modelingconcept0.797
  Ability of a model to predict its own outputs or behavior, sometimes distinguished from introspection.
• Attribution Similaritymethod0.796
  Correlating attribution vectors (feature activation × logit weight of next token) across model pairs to measure functional universality
• Self-Other Distinctionconcept0.787
  The implicit capacity the self-prior implements by assigning high density to familiar self-states and low density to non-self states
• Scaling Of The Selfconcept0.785
  Mechanisms by which smaller competent subunits bind into a higher-level Self with larger goals; key example via gap junction connections.