INDEX
Explanations
words or phrases related to sports events and player actions
New Auto-Interp
Negative Logits
ĸ
-0.16
èĥ¡
-0.15
belg
-0.15
zeÅĦ
-0.14
oin
-0.14
ï¸
-0.14
_nl
-0.14
Hamp
-0.13
ůj
-0.13
rices
-0.13
POSITIVE LOGITS
Yankees
0.22
Yankee
0.21
Bronx
0.21
cort
0.17
YES
0.15
Aberdeen
0.15
Tan
0.15
tsx
0.15
toi
0.15
Morr
0.15
Activations Density 0.064%