INDEX
Explanations
terms related to gender and gender equality issues
New Auto-Interp
Negative Logits
alez
-0.18
ãģıãĤĵ
-0.15
Richardson
-0.15
é¦ĸ
-0.14
sale
-0.14
WindowTitle
-0.14
fait
-0.14
DELAY
-0.14
FACE
-0.14
FD
-0.14
POSITIVE LOGITS
folk
0.17
bower
0.16
gender
0.16
autoload
0.16
bett
0.16
Outlined
0.15
Roz
0.15
Penal
0.15
osphere
0.15
crow
0.15
Activations Density 0.229%