INDEX
Explanations
names and titles of individuals
New Auto-Interp
Negative Logits
zioni
-0.17
vál
-0.15
iliz
-0.15
ίγ
-0.15
*__
-0.14
ickerView
-0.14
ίδα
-0.14
afari
-0.14
anzi
-0.14
bjerg
-0.14
POSITIVE LOGITS
Denis
0.17
yer
0.16
ors
0.16
extinct
0.14
or
0.14
711
0.14
stant
0.13
Vertical
0.13
ÃĵN
0.13
Heller
0.13
Activations Density 0.156%