INDEX
Explanations
proper nouns referring to individuals holding prestigious titles or positions
occurrences of titles or positions related to authority figures
New Auto-Interp
Negative Logits
crew
-0.86
fracture
-0.78
aukee
-0.77
icult
-0.76
sole
-0.75
estate
-0.71
compr
-0.71
ा
-0.70
camera
-0.69
overshadow
-0.68
POSITIVE LOGITS
Richard
1.12
Joseph
1.10
William
1.07
Theodore
1.07
Edward
1.04
David
1.04
Jonathan
1.04
Benjamin
1.04
Frank
1.04
Andrew
1.03
Activations Density 0.181%