INDEX
Explanations
instances of non-alphanumeric characters or punctuation marks
New Auto-Interp
Negative Logits
_
-0.54
IntoConstraints
-0.47
stretchr
-0.46
"]
-0.46
()]
-0.46
setupUi
-0.45
"];
-0.45
initWithFrame
-0.45
-0.44
Wund
-0.43
POSITIVE LOGITS
<bos>
1.40
Geplaatst
0.87
مُعرِّف
0.84
complexContent
0.83
Wicidata
0.80
Jereo
0.73
ècie
0.71
ویکیپدیا
0.71
francès
0.70
elemField
0.69
Activations Density 0.749%