INDEX
Explanations
phrases related to reasons or justifications
New Auto-Interp
Negative Logits
inian
-0.75
\/
-0.74
onto
-0.74
wanna
-0.72
à¼
-0.69
pmwiki
-0.69
regul
-0.69
gart
-0.68
Í
-0.67
--+
-0.67
POSITIVE LOGITS
it
0.92
critics
0.88
its
0.87
McAuliffe
0.84
analysts
0.83
differed
0.81
officials
0.80
lawmakers
0.80
proponents
0.80
organizers
0.79
Activations Density 0.510%