INDEX
Explanations
terms associated with male grooming, health, and masculinity-related topics
New Auto-Interp
Negative Logits
esh
-0.16
licate
-0.15
((__
-0.15
outil
-0.14
dle
-0.14
onis
-0.14
ty
-0.14
Flour
-0.14
Fay
-0.14
tle
-0.14
POSITIVE LOGITS
chor
0.15
aces
0.15
asonry
0.14
avo
0.14
ofil
0.14
adero
0.14
eph
0.14
EGA
0.14
eya
0.14
@stop
0.14
Activations Density 0.193%