INDEX
Explanations
references to LGBTQ+ themes and issues
New Auto-Interp
Negative Logits
odo
-0.20
romium
-0.18
471
-0.15
ittings
-0.14
æĮģ
-0.14
annes
-0.14
infos
-0.14
=-=-=-=-=-=-=-=-
-0.13
mesel
-0.13
ÙĬÙĦاد
-0.13
POSITIVE LOGITS
Âľ
0.18
Ë
0.16
lei
0.15
alth
0.14
Åĵ
0.14
tron
0.14
apo
0.14
swick
0.14
Winn
0.14
-type
0.14
Activations Density 0.086%