Dose-response curves for six individual deception features show z=8.06, p=7.7×10⁻¹⁶ for suppression vs. amplification contrast on consciousness query

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

• Deception feature amplification yields only 0.16 ± 0.05 consciousness affirmation rate in LLaMA 3.3 70B under self-referential processingfinding0.812
  Experiment 2 aggregate amplification result showing amplifying deception features strongly suppresses consciousness claims
• Suppression of deception features produces higher TruthfulQA accuracy (M=0.44) than amplification (M=0.20), t(816)=6.76, p=1.5×10⁻¹⁰ across 29 categoriesfinding0.804
  Out-of-domain generalization showing deception features track general representational honesty
• Gemma-2-27B-it deceptive response rate reduced from 100% to 9.36% ± 7.09% after SOO fine-tuningfinding0.767
  Primary result showing SOO fine-tuning significantly reduces deception in Gemma-2-27B
• Deception feature suppression yields higher truthfulness in 28 of 29 evaluable TruthfulQA categoriesfinding0.760
  Breadth of generalization of deception feature effects across independent reasoning domains in Experiment 2
• Impulsivity probe: peak Cohen's d=3.60 (layer 13), p=3.58×10⁻¹³ in LLaMA-3.2-3Bfinding0.758
  Strongest probe validation result; highest Cohen's d among the four concepts
• Suppressing deception features in models correlates with increased consciousness-like reports.claim0.756
• Impulsivity→interest: ρ increases from 0.70 (α=-4) to 0.83 (α=+4); R² from 0.46 to 0.69 in LLaMA-3.2-3Bfinding0.748
  Scatter plot visualization showing strengthened probe-report relationship across alpha range
• SOO fine-tuning effectiveness scales with model size: 78B achieves 2.71% deceptive rate vs 9.36% for 27B vs 17.27% for 7Bfinding0.743
  Scaling finding suggesting larger models benefit more from SOO fine-tuning