INDEX
Explanations
mentions of social classes, especially the middle class
references to the middle class and socioeconomic status
New Auto-Interp
Negative Logits
edIn
-0.93
Canaver
-0.77
quit
-0.75
ulously
-0.74
indal
-0.71
vernment
-0.70
conservancy
-0.70
atche
-0.69
vec
-0.68
igslist
-0.66
POSITIVE LOGITS
brow
1.11
finger
1.01
weight
0.98
weights
0.90
class
0.89
class
0.86
ground
0.83
fingers
0.82
aged
0.82
eastern
0.80
Activations Density 0.018%