INDEX
Explanations
words or phrases related to democracy and demographic topics
New Auto-Interp
Negative Logits
amer
-0.17
oje
-0.16
ious
-0.16
iously
-0.16
yb
-0.15
o
-0.15
aneously
-0.15
度
-0.15
heard
-0.15
ermo
-0.14
POSITIVE LOGITS
dem
0.24
anded
0.24
Dem
0.22
anding
0.20
urr
0.19
ands
0.19
oral
0.19
uestra
0.18
Dem
0.18
ographics
0.18
Activations Density 0.009%