INDEX
Explanations
names and titles associated with cultural or historical significance
New Auto-Interp
Negative Logits
landır
-0.15
lendi
-0.14
ollah
-0.13
adık
-0.13
KeySpec
-0.12
icros
-0.12
laÅŁtır
-0.12
IOR
-0.12
ephy
-0.11
Ñĥнок
-0.11
POSITIVE LOGITS
lem
0.42
LEM
0.40
vim
0.35
Bram
0.35
CIM
0.35
biom
0.35
rim
0.35
ģm
0.35
Fleming
0.35
Lem
0.35
Activations Density 0.671%