INDEX
Explanations
references to same-sex marriage and LGBTQ+ rights
New Auto-Interp
Negative Logits
utow
-0.16
ertiary
-0.14
Tencent
-0.13
BTS
-0.12
èĮĤ
-0.12
رض
-0.12
aras
-0.12
otas
-0.12
otos
-0.12
/setup
-0.12
POSITIVE LOGITS
marriage
0.50
Marriage
0.46
marriages
0.45
gay
0.40
mariage
0.39
å©ļ
0.36
weddings
0.36
couples
0.35
marital
0.35
marrying
0.35
Activations Density 0.051%