INDEX
Explanations
references to Barack Obama and his administration
New Auto-Interp
Negative Logits
aur
-0.15
çľł
-0.14
inand
-0.14
ings
-0.14
ì§ľ
-0.14
ãĥªãĥ¼ãĤº
-0.14
eries
-0.14
IES
-0.14
cing
-0.13
791
-0.13
POSITIVE LOGITS
izont
0.18
erture
0.15
moder
0.14
undry
0.14
Barack
0.14
irus
0.14
.portal
0.14
ियल
0.14
ænd
0.13
'gc
0.13
Activations Density 0.017%