INDEX
Explanations
references to George W. Bush and his administration
New Auto-Interp
Negative Logits
ees
-0.15
.ss
-0.15
uch
-0.15
alen
-0.15
jab
-0.15
Kings
-0.15
CALE
-0.15
éĺ¶
-0.14
öl
-0.14
.languages
-0.14
POSITIVE LOGITS
\common
0.15
allee
0.14
Ùĩ
0.14
imes
0.13
wick
0.13
Others
0.13
VEL
0.13
ÑĢоп
0.13
elter
0.13
Bund
0.13
Activations Density 0.007%