INDEX
Explanations
instances of sports-related scoring events or key plays
New Auto-Interp
Negative Logits
ायन
-0.17
gos
-0.15
anel
-0.15
istrovstvÃŃ
-0.15
çĽ
-0.15
=$
-0.14
ONO
-0.14
Alg
-0.14
RELEASE
-0.14
Kaynak
-0.14
POSITIVE LOGITS
drives
0.17
strup
0.17
Seam
0.16
XP
0.15
antino
0.14
hest
0.14
γαÏģ
0.14
udent
0.14
Juice
0.14
udas
0.14
Activations Density 0.384%