INDEX
Explanations
severe injury, wounds, and harm
New Auto-Interp
Negative Logits
チェック
0.72
Checkbox
0.72
රට
0.71
드리
0.71
প্রাস
0.69
sandbox
0.67
dropdown
0.66
Voting
0.66
Idle
0.66
greedy
0.66
POSITIVE LOGITS
injuries
3.96
injury
3.72
Injuries
3.49
Injury
3.27
injury
3.11
Injury
3.07
injured
3.06
wounds
2.91
Inj
2.89
injure
2.85
Activations Density 0.342%