INDEX
Explanations
references to Congress or congressional representatives
New Auto-Interp
Negative Logits
gether
-0.19
ÑģÑĤва
-0.14
uga
-0.14
-widgets
-0.14
aken
-0.14
conomics
-0.14
annes
-0.14
ektor
-0.14
rung
-0.14
ISTIC
-0.14
POSITIVE LOGITS
ional
0.40
woman
0.31
ion
0.29
arians
0.26
members
0.25
member
0.23
men
0.23
ionale
0.23
iona
0.23
man
0.22
Activations Density 0.024%