INDEX
Explanations
proper nouns, specifically names like "Dick."
occurrences of the name "Dick"
New Auto-Interp
Negative Logits
srf
-0.79
anwhile
-0.73
ccording
-0.73
adversity
-0.73
xual
-0.72
igated
-0.70
FUL
-0.70
PsyNetMessage
-0.69
yip
-0.68
76561
-0.66
POSITIVE LOGITS
enson
1.00
Cheney
0.89
ible
0.87
ie
0.86
erson
0.86
Grayson
0.83
inson
0.83
buster
0.81
Dick
0.81
ass
0.80
Activations Density 0.004%