INDEX
Explanations
statements related to political events and decision-making processes
New Auto-Interp
Negative Logits
herself
-0.67
elson
-0.63
Flickr
-0.60
himself
-0.60
penned
-0.59
Pain
-0.59
uttered
-0.59
aired
-0.59
âĺħ
-0.57
resides
-0.56
POSITIVE LOGITS
ourselves
1.73
our
0.91
ours
0.86
mble
0.81
%"
0.74
subcontract
0.73
manpower
0.72
.""
0.69
gonna
0.68
scrim
0.68
Activations Density 0.871%