INDEX
Explanations
references to the Star Wars franchise and its lore
New Auto-Interp
Negative Logits
etz
-0.17
ITOR
-0.16
yonel
-0.15
ież
-0.15
engin
-0.15
ög
-0.15
.Debugger
-0.15
umd
-0.15
İY
-0.15
fuse
-0.14
POSITIVE LOGITS
Jedi
0.26
Clone
0.22
obi
0.21
Darth
0.21
Republic
0.21
pad
0.20
ayla
0.20
Skywalker
0.20
Pad
0.18
Republic
0.18
Activations Density 0.032%