INDEX
Explanations
mentions of specific names or entities, particularly those related to individuals or political figures
New Auto-Interp
Negative Logits
WebElementEntity
-0.60
ConstraintSet
-0.60
titleMargin
-0.57
GenerationType
-0.56
webElementXpaths
-0.54
FontAwesomeIcon
-0.54
HomeAsUp
-0.54
Freien
-0.53
AnchorTagHelper
-0.52
ProgressHUD
-0.52
POSITIVE LOGITS
Del
0.94
DEL
0.93
Del
0.81
del
0.76
Delaney
0.72
DEL
0.70
<bos>
0.69
Dela
0.67
Dela
0.67
Delano
0.65
Activations Density 0.105%