INDEX
Explanations
references to body ownership and women's health empowerment
New Auto-Interp
Negative Logits
ãĤ¢
-0.24
-A
-0.21
_A
-0.20
ãĤ¢
-0.19
IJ
-0.17
ìķĦ
-0.16
pper
-0.16
ãĥ»ãĤ¢
-0.15
ad
-0.15
ÂłÐIJ
-0.15
POSITIVE LOGITS
Ł
0.17
-hover
0.16
jeme
0.16
ijo
0.15
Åijs
0.15
رÙĪØ´
0.15
Т
0.15
ongoose
0.15
ãĥĨ
0.14
SOR
0.14
Activations Density 0.068%