INDEX
Explanations
references to gender-specific competitions and events
New Auto-Interp
Negative Logits
uzzi
-0.16
ulo
-0.15
usercontent
-0.15
angkan
-0.15
zing
-0.14
stype
-0.14
elo
-0.14
imbus
-0.14
ncpy
-0.14
istrovstvÃŃ
-0.14
POSITIVE LOGITS
afari
0.17
indow
0.17
echa
0.14
arken
0.14
invert
0.14
231
0.13
consultation
0.13
eco
0.13
azor
0.13
Pend
0.13
Activations Density 0.014%