INDEX
Explanations
dialogue with quotes, the beginning of questions, and street abbreviations
New Auto-Interp
Negative Logits
-0.89
providedIn
-0.77
IUrlHelper
-0.76
#+#
-0.74
‘
-0.70
setVerticalGroup
-0.69
AddTagHelper
-0.69
ScopeManager
-0.69
rxjs
-0.66
(‘
-0.66
POSITIVE LOGITS
"
0.78
,"
0.65
."
0.61
\""
0.59
"
0.57
<bos>
0.54
@"
0.52
"
0.52
}"
0.50
”
0.50
Activations Density 4.989%