INDEX
Explanations
elements related to navigation menus and structure in web documents
New Auto-Interp
Negative Logits
اÙĦÙħÙĤ
-0.15
pll
-0.15
ies
-0.15
ilage
-0.15
Thur
-0.15
Visualization
-0.14
paste
-0.14
980
-0.14
portlet
-0.14
Holden
-0.14
POSITIVE LOGITS
.gg
0.18
онÑĮ
0.15
Ĺ
0.15
tern
0.14
Æł
0.14
.embed
0.14
fitte
0.14
anda
0.14
nings
0.14
缸
0.14
Activations Density 0.004%