INDEX
Explanations
mentions of races or teams in a competitive context
New Auto-Interp
Negative Logits
yg
-0.18
zac
-0.16
pecies
-0.15
gis
-0.15
sn
-0.14
idia
-0.14
prung
-0.14
acl
-0.14
egg
-0.13
esk
-0.13
POSITIVE LOGITS
è¤
0.15
anut
0.15
ä¹³
0.15
elson
0.15
iesz
0.14
leton
0.13
å§IJ
0.13
Sass
0.13
aled
0.13
adel
0.13
Activations Density 0.038%