INDEX
Explanations
mentions of a specific person named Martinez
references to the name "Martinez."
New Auto-Interp
Negative Logits
glers
-0.90
umbn
-0.89
pir
-0.82
umption
-0.80
cientious
-0.76
adder
-0.75
UTH
-0.75
iblings
-0.73
rencies
-0.73
tarian
-0.73
POSITIVE LOGITS
inez
1.10
Martinez
1.09
Mons
0.85
ards
0.76
Levy
0.73
da
0.70
ynski
0.69
Ortiz
0.69
Chavez
0.68
Clause
0.67
Activations Density 0.014%