Token-100 correlation persistence metric

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

• Emotion probe persistence (token-0 to token-100 correlation) in Cogito v2.1 is 0.214, compared to 0.099 for random unit vectors in 7168D space.finding0.763
  Quantitative measure of emotion feature persistence vs random baseline in Cogito
• autoregressive persistenceconcept0.731
  Baseline persistence of any probe direction arising from the autoregressive nature of LLMs, not specific to emotion content
• SAE feature firing probability persistence metricmethod0.730
  Persistence metric for SAE features: P(fires at t+100 | fired at t) minus P(fires at t+100 | did not fire at t)
• The persistence paradoxquestion0.729
  Core logical puzzle: if an agent does not change, it dies; if it changes, the self ceases to exist. Applies to all scales from organelles to evolutionary lineages.
• Persistence Paradoxconcept0.728
  Core logical paradox: if a species fails to change it dies; if it changes, it ceases to exist. Same applies to individuals.
• KV state persistence across steered tokensconcept0.726
  The causal steering experiment persists KV state over steered tokens so downstream effects can be observed without continued steering
• What is the appropriate metric for measuring representational alignment, given active debate on merits and deficiencies of all proposed measures?question0.722
  Open methodological question acknowledged as limitation
• What Is The Relationship Between Pattern Persistence Andquestion0.721