INDEX
Explanations
mentions of sports teams and their performances
New Auto-Interp
Negative Logits
iale
-0.15
heck
-0.15
PD
-0.15
hub
-0.15
ighb
-0.14
angl
-0.14
iele
-0.14
rieg
-0.14
stadt
-0.14
unker
-0.14
POSITIVE LOGITS
next
0.15
Lonely
0.15
hadn
0.14
åİŁæľ¬
0.14
travel
0.14
\API
0.14
:end
0.14
entine
0.14
enne
0.14
improve
0.14
Activations Density 0.059%