INDEX
Explanations
mentions of specific sports teams
New Auto-Interp
Negative Logits
ORMAL
-0.16
ADF
-0.15
jac
-0.15
šil
-0.15
cth
-0.15
¯
-0.14
ltre
-0.14
.ly
-0.14
dra
-0.14
utherford
-0.14
POSITIVE LOGITS
apo
0.15
šk
0.15
ož
0.14
Mi
0.14
Mi
0.14
#line
0.14
ylon
0.13
ugi
0.13
sông
0.13
WC
0.13
Activations Density 0.037%