INDEX
Explanations
throwing and catching balls
New Auto-Interp
Negative Logits
cuisses
0.39
ഞ്ചി
0.38
ओलंप
0.38
گفته
0.37
登山
0.37
選手
0.37
gymnast
0.37
齿
0.37
skiers
0.37
铎
0.37
POSITIVE LOGITS
throwing
0.99
Throw
0.97
Throw
0.96
throws
0.95
throw
0.92
threw
0.85
tossing
0.85
throwing
0.82
throw
0.80
抛
0.80
Activations Density 0.016%