INDEX
Explanations
the beginning of formatted sections in documents, often indicating structured content
Punctuation and symbols
numbers, dates, and punctuation
New Auto-Interp
Negative Logits
NUMX
-1.17
ſelf
-1.04
iſt
-1.03
―――――
-1.02
^(@)
-1.02
$_"
-0.98
Efq
-0.95
*/;
-0.95
myſelf
-0.93
***/
-0.91
POSITIVE LOGITS
<eos>
0.69
?
0.65
!
0.64
↵
0.61
^
0.61
<bos>
0.60
^
0.60
(
0.59
>
0.58
;
0.57
Activations Density 0.179%