INDEX
Explanations
HTML and JavaScript elements and attributes
New Auto-Interp
Negative Logits
textu
-0.14
Hur
-0.14
Guard
-0.13
hur
-0.13
ase
-0.13
äºŃ
-0.13
caffe
-0.13
newSize
-0.13
imm
-0.12
hotelu
-0.12
POSITIVE LOGITS
data
0.33
tabindex
0.30
title
0.29
role
0.27
rel
0.27
onclick
0.26
aria
0.25
tabIndex
0.24
aria
0.24
data
0.23
Activations Density 0.075%