INDEX
Explanations
references to specific districts or administrative divisions
New Auto-Interp
Negative Logits
ertest
-0.15
jour
-0.15
itates
-0.14
anuts
-0.14
erer
-0.14
films
-0.14
idla
-0.14
aign
-0.14
ktop
-0.14
alez
-0.14
POSITIVE LOGITS
wide
0.41
-wide
0.38
-level
0.34
-Level
0.29
Wide
0.27
/Area
0.27
/state
0.27
wide
0.26
boundaries
0.26
level
0.26
Activations Density 0.044%