INDEX
Explanations
references to fictional characters and settings
New Auto-Interp
Negative Logits
esi
-0.16
ader
-0.15
byss
-0.14
setQuery
-0.14
shint
-0.14
TERM
-0.14
Chancellor
-0.14
amaz
-0.14
ISR
-0.14
exports
-0.14
POSITIVE LOGITS
fred
0.16
oft
0.15
phas
0.14
ostel
0.14
ized
0.14
ize
0.14
cascade
0.14
umblr
0.14
Carm
0.14
ed
0.13
Activations Density 0.009%