INDEX
Explanations
names of people
names of individuals, particularly those with the first name "Brian."
New Auto-Interp
Negative Logits
USSR
-0.70
ModLoader
-0.67
Lanka
-0.66
Egyptians
-0.63
htar
-0.62
Dmit
-0.61
Payton
-0.61
partName
-0.61
Imran
-0.60
Petr
-0.60
POSITIVE LOGITS
iggs
0.84
aghan
0.80
andowski
0.78
ilver
0.71
ulo
0.66
auld
0.66
zen
0.66
wine
0.65
dry
0.65
fork
0.64
Activations Density 0.119%