INDEX
Explanations
terms related to same-sex relationships or marriage
references and discussions around same-sex relationships and marriage
New Auto-Interp
Negative Logits
unes
-0.79
ufact
-0.70
rote
-0.70
NCT
-0.70
tremend
-0.69
è¦ļéĨĴ
-0.67
amaz
-0.67
hower
-0.65
LIB
-0.64
NG
-0.63
POSITIVE LOGITS
uality
0.89
couples
0.77
piring
0.76
ually
0.74
bia
0.72
ounter
0.69
rights
0.69
discrimination
0.69
relations
0.68
supremacists
0.68
Activations Density 0.015%