INDEX
Explanations
references to the name "Mary."
New Auto-Interp
Negative Logits
Esposito
-0.72
premi
-0.71
Holt
-0.65
führt
-0.65
Nieto
-0.64
abit
-0.64
idon
-0.64
Dapper
-0.63
sik
-0.63
_^
-0.62
POSITIVE LOGITS
Mary
1.61
Mary
1.52
MARY
1.40
MARY
1.40
Marys
1.28
mary
1.23
gamma
1.03
mary
0.97
Gamma
0.96
Maryam
0.95
Activations Density 0.094%