INDEX
Explanations
instances of the name "Maria"
the name "Maria."
New Auto-Interp
Negative Logits
coded
-0.77
apped
-0.75
hire
-0.72
iliated
-0.71
sharing
-0.70
drawn
-0.69
onomy
-0.69
unal
-0.68
neys
-0.67
payer
-0.67
POSITIVE LOGITS
Maria
1.51
Maria
1.12
Teresa
1.02
Elena
1.02
Theresa
0.93
Isabel
0.89
Barbara
0.87
Rosa
0.86
ppa
0.85
Clara
0.84
Activations Density 0.007%