INDEX
Explanations
names and locations related to individuals in film and cinema
New Auto-Interp
Negative Logits
omy
-0.21
edla
-0.17
utenberg
-0.16
nova
-0.16
umlu
-0.16
ebek
-0.15
ż
-0.15
ALLERY
-0.15
ccione
-0.15
خاÙĨ
-0.14
POSITIVE LOGITS
ervo
0.18
erv
0.17
Subset
0.16
u
0.16
gress
0.16
ashire
0.16
enn
0.15
éϤ
0.15
ruptcy
0.15
ford
0.15
Activations Density 0.035%