INDEX
Explanations
mentions of sports teams and their contexts within articles
New Auto-Interp
Negative Logits
egas
-0.17
essim
-0.16
attern
-0.15
sed
-0.15
ropp
-0.14
mey
-0.14
$MESS
-0.14
lue
-0.14
ÃŃsto
-0.14
çľ
-0.14
POSITIVE LOGITS
ANNEL
0.15
Bow
0.15
Dys
0.15
Sav
0.14
bow
0.13
deflect
0.13
ouns
0.13
doi
0.13
ust
0.13
lic
0.13
Activations Density 0.008%