INDEX
Explanations
expressions of frustration and emotional reactions
New Auto-Interp
Negative Logits
AndEndTag
-0.56
Вікіпе
-0.52
numerusform
-0.52
HasAnnotation
-0.51
😉
-0.50
interested
-0.49
DialogInterface
-0.48
न्छ
-0.48
_)
-0.47
Interested
-0.47
POSITIVE LOGITS
Damn
1.03
damn
0.95
Damn
0.91
Ugh
0.90
ugh
0.89
dammit
0.88
damn
0.86
Dammit
0.85
wtf
0.85
damned
0.84
Activations Density 0.136%