INDEX
Explanations
variations of the word "bastard" in different contexts
New Auto-Interp
Negative Logits
uale
-0.16
slaught
-0.16
-ÑĤ
-0.15
.byId
-0.15
uate
-0.15
ırak
-0.15
ãģĵãģĿ
-0.15
ccione
-0.14
/inet
-0.14
isman
-0.14
POSITIVE LOGITS
anz
0.16
adm
0.15
orce
0.14
e
0.14
flu
0.14
mi
0.14
ero
0.14
pew
0.14
rophe
0.14
Yao
0.14
Activations Density 0.010%