INDEX
Explanations
references to social issues and inequalities
New Auto-Interp
Negative Logits
sp
-0.15
overs
-0.15
144
-0.14
andon
-0.14
itten
-0.14
å°¾
-0.14
Blanch
-0.14
ιδ
-0.13
.renderer
-0.13
ago
-0.13
POSITIVE LOGITS
anax
0.18
uco
0.16
IFORM
0.16
íĩ´
0.15
.native
0.15
quoise
0.15
áÄį
0.15
/pp
0.15
-prepend
0.14
apat
0.14
Activations Density 0.002%