INDEX
Explanations
references to players' performances in sports contexts
New Auto-Interp
Negative Logits
ваг
-0.14
vida
-0.14
anks
-0.14
ellido
-0.14
ApplicationContext
-0.14
invaded
-0.13
Major
-0.13
irus
-0.13
-dashboard
-0.13
uiltin
-0.13
POSITIVE LOGITS
opposing
0.17
effective
0.15
Neutral
0.15
对æĸ¹
0.15
INES
0.15
aerial
0.14
mism
0.14
vek
0.14
neutral
0.14
Bever
0.14
Activations Density 0.082%