Impulsivity→interest steering: probe entropy increases (LMM slope=0.024, p=2.30×10⁻⁴) but report entropy does not (p=0.11)

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

• Focus→wellbeing steering: both probe entropy (1.09→1.67 bits) and report entropy (0.88→1.69 bits) increase monotonically with αfinding0.852
  Evidence that improved introspection in focus→wellbeing arises from enriched internal state and report channels simultaneously
• Cross-concept steering: impulsivity→interest R² increases from 0.55 (α=-4) to 0.72 (α=+4), ∆R²=0.10, p=0.012 in LLaMA-3.2-3Bfinding0.843
  Second significant cross-concept introspection improvement; marginal after BH correction (q≈0.066)
• Impulsivity→interest: ρ increases from 0.70 (α=-4) to 0.83 (α=+4); R² from 0.46 to 0.69 in LLaMA-3.2-3Bfinding0.829
  Scatter plot visualization showing strengthened probe-report relationship across alpha range
• Wellbeing same-concept steering: LMM alpha slope=0.19, focus=0.40, interest=0.25, impulsivity=0.067 in LLaMA-3.2-3Bfinding0.813
  Quantifies per-concept effect size of same-concept steering on self-report
• Same-concept steering shifts self-report monotonically for all four concepts: LMM alpha slopes 0.067–0.40, all p<10⁻¹²finding0.797
  Causal confirmation that coupling between self-report and internal state is genuine; steering toward positive pole increases report
• Impulsivity probe: peak Cohen's d=3.60 (layer 13), p=3.58×10⁻¹³ in LLaMA-3.2-3Bfinding0.794
  Strongest probe validation result; highest Cohen's d among the four concepts
• Impulsivity concept: Spearman ρ=0.51, isotonic R²=0.31 in LLaMA-3.2-3B (n=400, p<10⁻¹²)finding0.790
  Third-strongest pooled introspective coupling in primary model
• Interest probe score drifts positively across turns: LMM slope=0.005, p=4.12×10⁻¹⁴ in LLaMA-3.2-3Bfinding0.790
  Demonstrates genuine internal-state dynamics in LLMs during multi-turn conversation