INDEX
Explanations
names of political figures and their associated titles
New Auto-Interp
Negative Logits
obec
-0.15
ucz
-0.15
ÙĤب
-0.14
buah
-0.14
ogh
-0.14
urm
-0.14
Registry
-0.14
Ãłn
-0.13
HandlerContext
-0.13
ookie
-0.13
POSITIVE LOGITS
(
0.17
581
0.16
675
0.15
Copyright
0.15
D
0.15
Rep
0.14
(D
0.14
Abram
0.14
trouble
0.14
haz
0.14
Activations Density 0.033%