INDEX
Explanations
punctuation marks and specific formatting elements in there text
New Auto-Interp
Negative Logits
ibre
-0.15
aminer
-0.15
лади
-0.15
Ñıн
-0.14
_UL
-0.14
ÑĤÑĢ
-0.14
úi
-0.14
.pe
-0.14
decess
-0.14
Flem
-0.14
POSITIVE LOGITS
ngr
0.15
warn
0.14
eyh
0.13
ziej
0.13
åĭ
0.13
Tata
0.13
région
0.13
Middleton
0.13
prive
0.12
ISC
0.12
Activations Density 0.018%