INDEX
Explanations
biographical descriptions or information
words related to biographies and biographical content
New Auto-Interp
Negative Logits
ulic
-0.69
hover
-0.68
urg
-0.66
oute
-0.65
olen
-0.64
near
-0.62
hof
-0.62
urgical
-0.61
usra
-0.60
Lind
-0.60
POSITIVE LOGITS
ographies
1.13
biography
0.99
ographical
0.87
ography
0.83
illum
0.78
autobiography
0.78
Surviv
0.75
Alv
0.73
ographers
0.70
escription
0.69
Activations Density 0.026%