INDEX
Explanations
mentions of wealth or wealthy individuals
terms associated with wealth and wealthy individuals
New Auto-Interp
Negative Logits
pty
-0.83
yrinth
-0.82
uberty
-0.81
Downloadha
-0.75
otide
-0.73
uality
-0.71
Airl
-0.70
PRESS
-0.69
shows
-0.69
ople
-0.68
POSITIVE LOGITS
earners
0.98
Institution
0.87
citiz
0.86
donors
0.84
landowners
0.81
Asians
0.80
philanthrop
0.76
redistribution
0.76
benef
0.76
holdings
0.75
Activations Density 0.014%