INDEX
Explanations
names containing 'Sch'
proper nouns, particularly names of individuals and places
New Auto-Interp
Negative Logits
faint
-0.72
REDACTED
-0.68
ForgeModLoader
-0.64
traffickers
-0.63
PLIC
-0.63
cember
-0.62
Aval
-0.62
centrif
-0.61
PDATE
-0.61
whales
-0.61
POSITIVE LOGITS
enegger
0.94
enger
0.88
schild
0.86
kov
0.82
inger
0.80
lich
0.79
itzer
0.79
berger
0.77
lain
0.76
atal
0.75
Activations Density 0.080%