INDEX
Explanations
biographical information about notable individuals, particularly focusing on their professions and nationalities
New Auto-Interp
Negative Logits
Duch
-0.16
eil
-0.15
atorial
-0.15
بÙĩ
-0.14
ej
-0.14
tm
-0.14
ielding
-0.14
echn
-0.13
yling
-0.13
ecurity
-0.13
POSITIVE LOGITS
polym
0.23
jur
0.17
phil
0.17
litter
0.17
zo
0.16
jur
0.16
prolific
0.16
polit
0.16
reform
0.15
bot
0.15
Activations Density 0.144%