INDEX
Explanations
mentions of socioeconomic class, particularly focusing on the middle class
references to the middle class
New Auto-Interp
Negative Logits
atche
-0.77
Canaver
-0.73
pedia
-0.71
00000
-0.68
ZI
-0.67
cci
-0.67
edIn
-0.67
utra
-0.66
raltar
-0.65
SIGN
-0.64
POSITIVE LOGITS
brow
0.85
piece
0.79
stad
0.74
middle
0.74
school
0.72
finger
0.71
weight
0.70
weights
0.70
ebted
0.70
tone
0.68
Activations Density 0.014%