INDEX
Explanations
mentions or references to the middle class
references to the middle class
New Auto-Interp
Negative Logits
atche
-0.74
Äį
-0.69
utra
-0.69
SIGN
-0.69
issance
-0.68
cci
-0.68
pedia
-0.68
Canaver
-0.67
00000
-0.67
ubi
-0.66
POSITIVE LOGITS
brow
0.86
piece
0.80
middle
0.77
finger
0.74
uve
0.73
stad
0.72
tone
0.70
actionGroup
0.70
pace
0.69
earners
0.69
Activations Density 0.014%