INDEX
Explanations
references to soccer or football matches, including actions, players, and scores
events and actions related to sports gameplay
New Auto-Interp
Negative Logits
netflix
-1.07
unemploy
-0.85
thood
-0.79
wiki
-0.78
onym
-0.78
Norn
-0.75
enegger
-0.74
nih
-0.74
encyclopedia
-0.73
è¦ļéĨĴ
-0.73
POSITIVE LOGITS
foul
0.87
halftime
0.86
teammate
0.83
stopp
0.80
tempo
0.79
decisive
0.78
score
0.77
batter
0.77
fren
0.75
frantic
0.75
Activations Density 0.635%