INDEX
Explanations
references to LGBTQ+ events and rights-related initiatives
New Auto-Interp
Negative Logits
antan
-0.14
eti
-0.14
elves
-0.13
pun
-0.13
etak
-0.13
aft
-0.13
Sul
-0.13
criteria
-0.12
ouis
-0.12
auer
-0.12
POSITIVE LOGITS
steller
0.18
olis
0.17
oker
0.17
HEME
0.16
ensi
0.15
erton
0.14
issant
0.14
ismu
0.14
ummings
0.14
ERT
0.14
Activations Density 0.263%