INDEX
Explanations
specific references to voting or electoral decisions
New Auto-Interp
Negative Logits
ạn
-0.17
kå
-0.17
igel
-0.17
oom
-0.16
atica
-0.15
.onCreate
-0.15
atches
-0.15
anders
-0.15
osphere
-0.14
ramework
-0.14
POSITIVE LOGITS
options
0.16
age
0.14
à¥īल
0.14
asin
0.13
options
0.13
erot
0.13
Harmony
0.12
688
0.12
051
0.12
788
0.12
Activations Density 0.041%