INDEX
Explanations
content indicating to scroll down for more information or continuation of a text
repeated instructions to scroll or navigate through content
New Auto-Interp
Negative Logits
ICAN
-0.66
Commun
-0.65
aging
-0.65
ãĤ¤ãĥĪ
-0.63
bage
-0.62
anza
-0.61
jri
-0.60
DN
-0.60
rov
-0.60
emet
-0.58
POSITIVE LOGITS
gallery
0.74
thumbnail
0.71
enlarg
0.65
circles
0.64
cursor
0.64
enlarge
0.63
scrolling
0.60
snippet
0.60
scroll
0.59
menus
0.59
Activations Density 0.057%