INDEX
Explanations
mentions of political figures and their actions regarding LGBTQ+ issues or related events
New Auto-Interp
Negative Logits
pb
-0.16
åĺĽ
-0.15
apt
-0.15
aggable
-0.14
ãĤ¤ãĥĪ
-0.14
ital
-0.14
ora
-0.14
Fus
-0.14
idual
-0.14
Carp
-0.14
POSITIVE LOGITS
unused
0.15
mote
0.14
/Users
0.14
elin
0.14
dů
0.14
esser
0.13
itere
0.13
Blockly
0.13
bron
0.13
lá
0.13
Activations Density 0.162%