INDEX
Explanations
terms and concepts related to feminism and feminine identity
New Auto-Interp
Negative Logits
iol
-0.18
æģ¯
-0.16
Chill
-0.15
iggers
-0.15
Carnegie
-0.14
iola
-0.14
ebek
-0.13
elig
-0.13
leton
-0.13
pd
-0.13
POSITIVE LOGITS
inity
0.30
ine
0.26
inine
0.23
icide
0.21
inely
0.20
azi
0.19
icides
0.19
INE
0.19
oir
0.18
ine
0.16
Activations Density 0.007%