INDEX
Explanations
information related to historical figures and their life events
New Auto-Interp
Negative Logits
.retrieve
-0.15
ITE
-0.15
amble
-0.15
oola
-0.14
endale
-0.14
ollo
-0.14
Ñıг
-0.14
erto
-0.14
idden
-0.14
prite
-0.14
POSITIVE LOGITS
UNKNOWN
0.19
Unknown
0.17
died
0.17
Unknown
0.16
Twin
0.16
Twins
0.15
living
0.15
living
0.15
res
0.14
unk
0.14
Activations Density 0.008%