Text-based and self-steered emotionality ratings are only weakly correlated (ρ = +0.051, n.s.), suggesting they measure different aspects of feature emotionality.

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

• Correlation between self-evaluation and textual evaluation of SAE feature emotionality: rho=+0.051 (n.s.)finding0.838
  Shows that the two evaluation methods for emotionality are largely uncorrelated, indicating they capture different signals
• Textual evaluation and agentic self-evaluation of SAE feature emotionality measure different aspects of emotional content and correlate only weakly (rho=+0.051, n.s.)claim0.836
  Interprets the near-zero correlation between the two evaluation methods as evidence they capture distinct signals
• Self-evaluated emotionality and textual evaluation of SAE features predict persistence in opposite directions.claim0.819
  Surprising finding that the two evaluation methods diverge in their relationship with persistence
• The correlation between emotion subspace fraction and self-evaluated emotionality validates that emotion probe concepts somewhat overlap with the model's self-reported internal emotions.claim0.813
  Claim supporting the validity of the probe construction method via cross-validation with self-report
• Self-evaluated emotionality of SAE features negatively correlates with activation variance explained (ρ = -0.184, p = 4.6e-09), requiring variance correction to reveal the persistence signal.finding0.811
  Explains why variance correction is needed to see the self-evaluation–persistence relationship
• Textual evaluation emotionality weakly negatively correlates with SAE feature persistencefinding0.803
  Contrasts with positive correlation from agentic self-evaluation, suggesting text and self-evaluation capture different aspects
• Is the stronger persistence-emotionality relationship from self-evaluation due to introspection quality, or merely due to ability to test additional steering strengths including negative?question0.798
  Open methodological question about the source of the agentic self-evaluation advantage
• The relationship between persistence and self-evaluated emotionality serves as a replication of probe-based findings without shared confounds from probe constructionclaim0.794
  Claims that agentic self-evaluation provides independent convergent evidence for emotion-persistence link