INDEX
Negative Logits
megs
-0.08
RTWF
-0.08
.jface
-0.08
firef
-0.08
Brig
-0.08
Prosper
-0.08
_BRANCH
-0.08
proportional
-0.08
Missions
-0.08
Quick
-0.08
POSITIVE LOGITS
transgender
0.19
_gender
0.13
queer
0.12
Gender
0.12
gender
0.12
LGBTQ
0.12
genders
0.12
.gender
0.12
Gender
0.11
femin
0.11
Activations Density 0.037%