INDEX
Explanations
mentions of Ottoman-related entities and concepts
New Auto-Interp
Negative Logits
izon
-0.16
AREST
-0.15
agogue
-0.14
.Factory
-0.14
خارجÙĬØ©
-0.14
ÄĽÅ¾
-0.14
yan
-0.14
ÑĤоÑİ
-0.14
åĽ³
-0.14
aguay
-0.14
POSITIVE LOGITS
omp
0.16
ting
0.15
diss
0.15
odor
0.15
inker
0.15
alley
0.15
resden
0.14
ture
0.14
olid
0.14
berg
0.14
Activations Density 0.015%