INDEX
Explanations
mentions of locations, particularly in reference to cities and regions
New Auto-Interp
Negative Logits
/Gate
-0.15
lix
-0.15
yna
-0.15
nap
-0.15
oman
-0.15
akis
-0.14
zano
-0.14
ÙĦاÙģ
-0.14
ritch
-0.13
Albania
-0.13
POSITIVE LOGITS
Astr
0.28
Perm
0.28
Od
0.27
Nov
0.26
Perm
0.26
Vor
0.23
Sar
0.22
Adler
0.21
Sm
0.21
Nov
0.21
Activations Density 0.082%