INDEX
Explanations
phrases related to birth, death, and life events
New Auto-Interp
Negative Logits
ghan
-0.16
inker
-0.15
rike
-0.15
uke
-0.14
egin
-0.14
roker
-0.14
agan
-0.14
igue
-0.14
ien
-0.14
ÃŃd
-0.14
POSITIVE LOGITS
near
0.16
into
0.16
near
0.15
Near
0.14
on
0.14
èģ
0.14
ONENT
0.14
UMMY
0.14
олÑİ
0.13
неÑĤ
0.13
Activations Density 0.028%