INDEX
Explanations
references to citizens and civic engagement
New Auto-Interp
Negative Logits
orian
-0.21
tk
-0.16
ding
-0.15
YA
-0.15
svn
-0.15
dim
-0.15
RootElement
-0.15
ds
-0.14
usp
-0.14
ors
-0.14
POSITIVE LOGITS
hood
0.22
stvo
0.16
belt
0.16
½
0.15
ACHI
0.15
suit
0.15
empre
0.14
RI
0.14
0.14
mapped
0.14
Activations Density 0.019%