INDEX
Explanations
mentions of political figures, particularly US presidents
mentions of the word "President" and context related to presidential actions or statuses
New Auto-Interp
Negative Logits
opter
-0.73
saddle
-0.63
hitch
-0.62
hump
-0.62
attr
-0.62
NRS
-0.60
nesota
-0.60
fork
-0.60
brim
-0.60
corrid
-0.59
POSITIVE LOGITS
ially
1.23
ial
1.20
IAL
1.01
doms
0.85
hip
0.73
Mahmoud
0.73
emer
0.71
ional
0.71
Hassan
0.70
ual
0.70
Activations Density 0.069%