INDEX
Explanations
occurrences of the name "Marie" and its variations
New Auto-Interp
Negative Logits
irl
-0.15
uw
-0.15
rus
-0.14
æģĴ
-0.14
orer
-0.14
gaps
-0.14
.templates
-0.14
ox
-0.14
akin
-0.13
swire
-0.13
POSITIVE LOGITS
ke
0.22
Louise
0.17
holm
0.16
-La
0.16
nty
0.16
份
0.16
annel
0.15
eniz
0.15
Cur
0.15
ault
0.15
Activations Density 0.007%