INDEX
Explanations
actions related to physical sports or activities
phrases indicating possession or acquisition in the context of sports
New Auto-Interp
Negative Logits
verend
-0.74
hide
-0.74
SPONSORED
-0.73
ataka
-0.65
Suggest
-0.63
anguages
-0.63
ulhu
-0.63
figure
-0.60
speak
-0.59
Chapter
-0.59
POSITIVE LOGITS
rewarded
1.12
punished
0.97
rid
0.94
bumped
0.94
hammered
0.91
pounded
0.91
beaten
0.91
knocked
0.89
blown
0.85
stronger
0.85
Activations Density 0.086%