Pearson correlation of 0.74 between A/1/3450 activation and Arabic script proxy over 40M tokens

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

• Binarized DNA proxy has Pearson correlation of 0.80 with A/1/2937 feature activationsfinding0.840
  Demonstrates specificity and sensitivity of DNA feature
• Arabic feature A/1/3450 and B/1/1334 have activation correlation of 0.91 across 40M tokensfinding0.837
  Demonstrates universality of the Arabic script feature across two independently trained transformers
• Arabic script feature A/1/3450 fires on 81% Arabic-script tokens when active, with 98% specificity at high activation levelsfinding0.800
  Demonstrates activation specificity of the Arabic script sparse autoencoder feature
• Hebrew feature A/1/416 and B/1/1901 have activation correlation of 0.92finding0.757
  Universality of Hebrew script feature across two transformers
• Base64 feature A/1/2357 and B/1/2165 have activation correlation of 0.85finding0.755
  Universality of base64 feature across two transformers
• Feature pair A/1/3949 and B/1/3321 have activation correlation 0.98 but negative logit weight correlation, firing on PLOSOne journal abbreviationsfinding0.751
  Demonstrates that activation similarity can diverge from logit weight similarity due to interference
• DNA feature A/1/2937 and B/1/3680 have activation correlation of 0.92finding0.749
  Universality of DNA feature across two transformer models with different random seeds
• Correlation r=0.999 between detection-adjusted logit difference and control logit increase across all 40 layer-strength configurationsfinding0.749
  Key quantitative evidence that detection signal is identical to global logit shift confound