INDEX
Explanations
references to biblical or religious texts and their interpretations
New Auto-Interp
Negative Logits
-0.15
liÄŁe
-0.13
èĩªæ²»
-0.13
foul
-0.12
et
-0.12
â
-0.12
Ú©Ø´
-0.12
expans
-0.12
(çģ«
-0.12
mund
-0.11
POSITIVE LOGITS
TokenName
0.19
erotische
0.16
_tF
0.15
ÙĦÙĥتر
0.15
_mD
0.15
Mitar
0.15
adolu
0.15
adele
0.15
eskort
0.15
ROM
0.15
Activations Density 7.261%