INDEX
Explanations
double quotes that likely indicate speech
quotation marks
New Auto-Interp
Negative Logits
‘
-1.91
'
-1.52
、『
-1.37
『
-1.34
‚
-1.23
(‘
-1.19
。『
-1.16
‘
-1.02
『
-1.02
SuspendLayout
-1.01
POSITIVE LOGITS
-"
1.01
>"
0.98
//"
0.91
—"
0.90
--"
0.90
".
0.88
|"
0.87
.."
0.87
@"
0.86
"*",
0.86
Activations Density 0.733%