INDEX
Explanations
references to sexual orientation, particularly related to being gay or LGBTQ+ issues
New Auto-Interp
Negative Logits
FIA
-0.44
cooperation
-0.44
الحياه
-0.44
vigilance
-0.44
conflict
-0.44
Uda
-0.43
녁
-0.41
וש
-0.41
granule
-0.41
papyrus
-0.41
POSITIVE LOGITS
gay
1.16
homosexual
0.99
gay
0.97
gays
0.91
homosexuality
0.87
LGBT
0.85
GAY
0.82
lesbian
0.82
LGBTQ
0.82
LGBT
0.81
Activations Density 0.293%