INDEX
Explanations
references to gender representation in various media
New Auto-Interp
Negative Logits
alary
-0.17
زÙĪ
-0.15
azy
-0.15
eneg
-0.14
Descriptors
-0.14
rencont
-0.14
LBL
-0.14
ίÏīν
-0.14
ugi
-0.14
usat
-0.14
POSITIVE LOGITS
Quant
0.17
apas
0.16
ooth
0.15
quantities
0.15
ups
0.14
Nordic
0.14
Quantity
0.14
Glob
0.14
odox
0.14
quantity
0.14
Activations Density 0.090%