INDEX
Explanations
names of individuals and their associated institutions
New Auto-Interp
Negative Logits
teil
-0.21
vé
-0.17
shine
-0.17
vell
-0.16
gie
-0.15
gy
-0.15
angelo
-0.15
vant
-0.14
seite
-0.14
Tro
-0.14
POSITIVE LOGITS
رÙĪØ¯
0.16
eso
0.15
348
0.14
EDIA
0.14
anc
0.14
stab
0.14
ault
0.14
auer
0.14
_ib
0.14
ì²Ń
0.14
Activations Density 0.078%