INDEX
Explanations
occurrences of HTML elements and attributes related to script and style links
New Auto-Interp
Negative Logits
olet
-0.16
ibold
-0.15
uther
-0.14
_triggered
-0.14
atre
-0.14
waivers
-0.14
inks
-0.14
ocker
-0.13
owie
-0.13
olulu
-0.13
POSITIVE LOGITS
OfClass
0.16
WithOptions
0.16
0.16
ponce
0.15
chio
0.15
mps
0.15
ÙĨب
0.14
_STS
0.14
istrovstvÃŃ
0.14
Hoe
0.14
Activations Density 0.002%