INDEX
Explanations
references to unrest or conflict happening in urban environments
mentions of "streets" in various contexts
New Auto-Interp
Negative Logits
igham
-0.78
itors
-0.75
ITED
-0.75
opsis
-0.73
emort
-0.71
itor
-0.70
ary
-0.69
aron
-0.68
ARI
-0.68
isman
-0.66
POSITIVE LOGITS
cape
1.21
fare
0.95
streets
0.95
walker
0.93
walk
0.86
wear
0.86
ffiti
0.78
cars
0.77
sew
0.75
ways
0.74
Activations Density 0.019%