Correlation r=0.999 between detection-adjusted logit difference and control logit increase across all 40 layer-strength configurations

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

• At layer 0 α=5, detection-adjusted logit difference is +3.19 and control increase is +3.22, a difference of only 0.03 logitsfinding0.886
  Concrete numerical example showing detection and control are nearly identical at peak apparent accuracy
• Binary detection accuracy (up to 97.3% at L0 α=5) is entirely explained by global logit shifts (r=0.999 correlation with control)finding0.820
  Core negative result: the binary detection paradigm cannot distinguish genuine introspection from uniform output bias
• Net detection signal (detection minus control) is near-zero across all 40 layer-strength configurations: mean = -0.01 ± 0.03 logitsfinding0.799
  Quantitative evidence that binary detection provides no genuine introspection signal beyond global logit shifts
• Binary detection adjusted accuracy reaches 97.3% at layer 0 with α=5 before baseline control is appliedfinding0.789
  The misleadingly high result that prior paradigm would report as evidence of introspection
• Strength comparison accuracy averages 47% at layers 15-30, indistinguishable from 50% chancefinding0.771
  Shows collapse of introspective capability at later layers in the strength comparison task
• Correlation between layer-wise scores and task accuracy ρ = −0.73 (p < 0.001) on LLaMAfinding0.762
  Core E3 finding validating S as a predictor of anchoring effectiveness
• Feature pair A/1/3949 and B/1/3321 have activation correlation 0.98 but negative logit weight correlation, firing on PLOSOne journal abbreviationsfinding0.762
  Demonstrates that activation similarity can diverge from logit weight similarity due to interference
• Strength comparison accuracy reaches 73% at layer 3 for injection pair (2,6) vs. 50% chancefinding0.760
  Secondary positive result for strength comparison showing graded sensitivity to perturbation magnitude