INDEX
Explanations
phrases related to social and legal issues involving discrimination, rights, and regulations
concepts and discussions related to human rights and social justice issues
New Auto-Interp
Negative Logits
iple
-0.64
rename
-0.61
Nin
-0.61
çͰ
-0.59
nir
-0.58
APTER
-0.57
Discord
-0.56
Begins
-0.55
enthusi
-0.55
BSD
-0.54
POSITIVE LOGITS
illegally
0.87
unlawfully
0.81
lawfully
0.79
angering
0.75
unfavorable
0.75
improperly
0.75
illicit
0.74
infringing
0.71
or
0.70
infring
0.70
Activations Density 1.138%