INDEX
Explanations
references to sports teams and their performance
New Auto-Interp
Negative Logits
eÄį
-0.17
imb
-0.16
APER
-0.14
ãĥ³ãĤ¯
-0.13
kili
-0.13
uci
-0.13
æĪ
-0.13
ersiz
-0.13
·
-0.13
Nev
-0.13
POSITIVE LOGITS
shire
0.14
Increment
0.14
ois
0.14
685
0.14
ussen
0.14
onaut
0.13
ampie
0.13
797
0.13
sur
0.13
aur
0.13
Activations Density 0.045%