INDEX
Explanations
mentions of the name "Mary."
New Auto-Interp
Negative Logits
kova
-0.17
hower
-0.16
otive
-0.16
FAQ
-0.16
urge
-0.16
ayet
-0.15
arna
-0.15
staw
-0.15
лем
-0.15
mach
-0.14
POSITIVE LOGITS
ann
0.22
sville
0.20
Ann
0.20
mount
0.19
borough
0.19
ellen
0.19
Ellen
0.19
beth
0.19
lin
0.18
trs
0.18
Activations Density 0.008%