INDEX
Explanations
specific patterns or markers indicative of stylistic elements in text
New Auto-Interp
Negative Logits
iox
-0.16
ög
-0.16
cape
-0.15
AMA
-0.15
Pend
-0.14
/proto
-0.14
incip
-0.14
Seks
-0.14
ization
-0.14
seksi
-0.14
POSITIVE LOGITS
ì´
0.16
byt
0.15
Nes
0.15
lok
0.15
ellas
0.14
íĮIJ
0.14
ook
0.14
ëĮĢìĿĺ
0.14
okol
0.14
/posts
0.13
Activations Density 0.053%