INDEX
Explanations
mentions of economic or social inequality
references to various forms of inequality
New Auto-Interp
Negative Logits
bs
-0.80
Kiss
-0.71
oe
-0.68
Mem
-0.67
Jelly
-0.66
ze
-0.66
bb
-0.64
ven
-0.64
ams
-0.64
Alert
-0.63
POSITIVE LOGITS
inequality
3.46
inequalities
2.76
equality
2.29
inequ
1.99
equality
1.96
unequal
1.78
injustice
1.72
disparities
1.72
disparity
1.65
Equality
1.51
Activations Density 0.021%