INDEX
Explanations
components related to technology and media
New Auto-Interp
Negative Logits
aja
-0.14
Shut
-0.13
Hund
-0.13
itech
-0.13
ice
-0.12
æIJį
-0.12
abbage
-0.12
angi
-0.12
stroj
-0.12
polož
-0.12
POSITIVE LOGITS
ÂŃing
0.15
itele
0.15
leurs
0.14
koli
0.14
lesi
0.14
kab
0.14
reau
0.13
cka
0.13
eya
0.13
obao
0.13
Activations Density 0.014%