INDEX
Explanations
references to former president George W. Bush and associated political figures
New Auto-Interp
Negative Logits
éĺ¶
-0.16
alen
-0.15
nodoc
-0.15
ovat
-0.15
Thá»ĭ
-0.15
ees
-0.15
ione
-0.14
rint
-0.14
ogy
-0.14
rof
-0.14
POSITIVE LOGITS
Ùĩ
0.16
allee
0.15
\common
0.15
aroo
0.14
795
0.14
&r
0.14
contrario
0.13
Bray
0.13
elter
0.13
Bund
0.13
Activations Density 0.005%