INDEX
Explanations
terms and concepts related to feminism and femininity
New Auto-Interp
Negative Logits
iol
-0.18
Duch
-0.15
lier
-0.15
ocking
-0.15
liers
-0.15
·æĸ°
-0.14
icker
-0.14
.defaults
-0.14
ìļ´ëĵľ
-0.14
pd
-0.14
POSITIVE LOGITS
inity
0.30
ine
0.25
azi
0.22
inine
0.21
icide
0.21
icides
0.20
oir
0.19
inely
0.19
INE
0.17
icÃŃ
0.16
Activations Density 0.006%