INDEX
Explanations
anatomical body parts
references to anatomy, animals, and mythical beings
New Auto-Interp
Negative Logits
APD
-0.78
osure
-0.73
Administ
-0.73
cture
-0.72
VB
-0.72
ĩ
-0.69
Ins
-0.67
iscons
-0.67
»Ĵ
-0.67
lvl
-0.66
POSITIVE LOGITS
?,
0.90
bows
0.89
dolls
0.87
boobs
0.81
emoji
0.80
poop
0.80
dancing
0.80
penis
0.79
frogs
0.79
worms
0.79
Activations Density 0.666%