INDEX
Explanations
mentions of birth and death events
New Auto-Interp
Negative Logits
egin
-0.16
ghan
-0.16
пон
-0.15
olini
-0.15
ias
-0.14
iterals
-0.14
eki
-0.14
ien
-0.14
/from
-0.14
uke
-0.14
POSITIVE LOGITS
near
0.15
prematurely
0.14
ONENT
0.14
near
0.14
gota
0.14
Near
0.14
ëı
0.14
неÑĤ
0.13
INY
0.13
ojis
0.13
Activations Density 0.028%