INDEX
Explanations
sections or elements in documents, particularly markings like brackets and asterisks signaling emphasis or organization
New Auto-Interp
Negative Logits
↵↵
-0.80
↵↵↵
-0.79
webElementXpaths
-0.73
/
-0.69
,
-0.68
SharedDtor
-0.66
[…]
-0.62
to
-0.62
-0.62
in
-0.62
POSITIVE LOGITS
?}
0.92
.}
0.83
-}
0.81
!}
0.77
:}
0.76
conseguenze
0.73
""}
0.72
chrétiens
0.72
colorés
0.71
niedersachsen
0.69
Activations Density 0.017%