INDEX
Explanations
references to the LGBTQ+ community, specifically focusing on lesbian individuals
terms related to lesbian identity and community
New Auto-Interp
Negative Logits
ULE
-0.90
æĸ¹
-0.82
EY
-0.81
frames
-0.80
alez
-0.76
Seym
-0.74
urers
-0.73
*/(
-0.73
lamm
-0.71
eele
-0.71
POSITIVE LOGITS
lesbian
0.91
couples
0.90
separat
0.89
ism
0.88
bisexual
0.85
separatist
0.82
sex
0.82
emancipation
0.78
ization
0.77
Lesbian
0.77
Activations Density 0.012%