INDEX
Explanations
mentions of specific sports teams and their respective performance metrics
New Auto-Interp
Negative Logits
رب
-0.17
icers
-0.17
apiro
-0.16
ebx
-0.15
iais
-0.15
Kaplan
-0.15
ãĥ³ãĤ¿
-0.14
angs
-0.14
ullan
-0.13
Slf
-0.13
POSITIVE LOGITS
av
0.16
u
0.15
@$_
0.14
arella
0.14
ampie
0.13
bum
0.13
dc
0.13
anh
0.13
itchen
0.13
code
0.13
Activations Density 0.057%