INDEX
Explanations
occurrences of punctuation and specific stylistic markers in text
New Auto-Interp
Negative Logits
eç
-0.15
βο
-0.14
919
-0.14
WidgetItem
-0.14
Demp
-0.14
cape
-0.14
abra
-0.14
CHR
-0.13
IALIZ
-0.13
olders
-0.13
POSITIVE LOGITS
ews
0.17
нка
0.17
obot
0.16
igel
0.14
haven
0.14
andal
0.13
umber
0.13
mour
0.13
ondon
0.13
rette
0.13
Activations Density 0.000%