INDEX
Explanations
terms and concepts related to gender issues and equality
New Auto-Interp
Negative Logits
born
-0.14
orners
-0.14
urr
-0.14
ograd
-0.14
ei
-0.13
sale
-0.13
electrom
-0.13
GOODMAN
-0.13
incinn
-0.13
sky
-0.13
POSITIVE LOGITS
fol
0.17
à¸Ĭาà¸ķ
0.16
ed
0.16
Ves
0.15
åĪ¥
0.15
mine
0.15
edBy
0.15
ë§ģ
0.15
edList
0.15
ovÄĽ
0.15
Activations Density 0.017%