INDEX
Explanations
punctuated dialogue or speech within the text
New Auto-Interp
Negative Logits
Personensuche
-0.99
Normdatei
-0.78
AssemblyCulture
-0.78
وتسجيلات
-0.77
SharedDtor
-0.75
AsUp
-0.75
::~
-0.68
Мексичка
-0.68
Italijanski
-0.67
</tfoot>
-0.66
POSITIVE LOGITS
"
0.67
是啊
0.61
“
0.57
“
0.53
「
0.53
("0.51
Ignoring
0.50
nodding
0.50
Yeah
0.49
awtextra
0.48
Activations Density 0.036%