INDEX
Explanations
proper nouns and names associated with a local event
New Auto-Interp
Negative Logits
avad
-0.17
δικ
-0.15
acey
-0.14
Wid
-0.14
Jaw
-0.13
avis
-0.13
iolet
-0.13
uckle
-0.13
reak
-0.13
undry
-0.13
POSITIVE LOGITS
SKIP
0.17
εÏĦ
0.17
³
0.16
izin
0.15
irical
0.15
Kür
0.15
viron
0.15
eskort
0.15
aliz
0.15
uzu
0.14
Activations Density 0.023%