INDEX
Explanations
mentions of individuals and their experiences related to LGBTQ+ events or issues
New Auto-Interp
Negative Logits
ares
-0.15
ãĥ¥ãĥ¼
-0.15
ãģªãģĮ
-0.15
aris
-0.14
æľ
-0.14
_rq
-0.14
inkel
-0.14
esar
-0.14
رÙĩ
-0.14
åı¸
-0.14
POSITIVE LOGITS
special
0.16
issen
0.16
uran
0.15
tring
0.15
ulle
0.15
اÙĦÙģ
0.15
odata
0.14
olia
0.14
lette
0.14
strom
0.14
Activations Density 0.003%