INDEX
Explanations
mentions of the name "Liz" and its variations
New Auto-Interp
Negative Logits
erin
-0.18
esin
-0.17
er
-0.17
igne
-0.16
stin
-0.16
ed
-0.15
erse
-0.15
ÑģÑĤав
-0.15
esub
-0.15
es
-0.15
POSITIVE LOGITS
zi
0.28
zy
0.22
ze
0.21
quierda
0.21
ionario
0.21
t
0.20
y
0.20
zen
0.20
s
0.20
zych
0.19
Activations Density 0.022%