INDEX
Explanations
terms related to romance literature and character dynamics
New Auto-Interp
Negative Logits
_YUV
-0.16
fm
-0.16
zcze
-0.16
-0.15
Vimeo
-0.15
documentary
-0.15
rt
-0.14
ĺ
-0.14
odes
-0.14
vrier
-0.14
POSITIVE LOGITS
fic
0.28
fandom
0.23
canon
0.21
prompts
0.20
fic
0.19
Warnings
0.18
cannon
0.18
.chapter
0.18
fan
0.18
prompt
0.18
Activations Density 0.236%