INDEX
Explanations
references to places of birth or locations associated with individuals
New Auto-Interp
Negative Logits
arton
-0.16
468
-0.15
brook
-0.15
enso
-0.15
ibold
-0.15
idl
-0.15
寧
-0.14
umn
-0.14
_FF
-0.14
elder
-0.14
POSITIVE LOGITS
ennie
0.15
ENARIO
0.15
Ney
0.15
resultSet
0.14
ieri
0.13
thouse
0.13
Hierarchy
0.13
Belediyesi
0.13
zÄĻ
0.13
pol
0.13
Activations Density 0.023%