INDEX
Explanations
references to authors and their works, particularly in the context of LGBTQ literature
New Auto-Interp
Negative Logits
elia
-0.07
pecia
-0.07
eyse
-0.07
ectors
-0.07
AGMA
-0.07
eydi
-0.06
NV
-0.06
Zaman
-0.06
erp
-0.06
endale
-0.06
POSITIVE LOGITS
енÑģ
0.07
Benchmark
0.07
νÏī
0.06
Anthrop
0.06
GIN
0.06
udios
0.06
.jd
0.06
taÅŁ
0.06
å®ĺç½ij
0.06
aru
0.06
Activations Density 0.011%