INDEX
Explanations
special characters and punctuation marks in the text
New Auto-Interp
Negative Logits
‘
-0.88
RenderAtEndOf
-0.74
(‘
-0.69
==='
-0.69
'
-0.68
=',
-0.65
』『
-0.63
>';
-0.62
,’
-0.61
'../
-0.59
POSITIVE LOGITS
……"
0.90
Cæsar
0.78
ſtate
0.76
uſe
0.74
quæ
0.71
...."
0.69
)".
0.69
\""
0.68
nonUne
0.68
>{"0.67
Activations Density 0.195%