INDEX
Explanations
references to various capitals or important cities and locations
New Auto-Interp
Negative Logits
smith
-0.15
berger
-0.14
Ĵáŀ
-0.14
hud
-0.13
Aspect
-0.13
zsche
-0.13
Hod
-0.13
aight
-0.13
adel
-0.13
-schema
-0.13
POSITIVE LOGITS
city
0.32
city
0.24
town
0.24
åŁİå¸Ĥ
0.23
-city
0.22
cities
0.21
гоÑĢода
0.21
cittÃł
0.20
cidade
0.20
Stadt
0.19
Activations Density 0.050%