INDEX
Explanations
the name "Tommy."
references to the name "Tommy."
New Auto-Interp
Negative Logits
ividual
-0.87
icted
-0.82
elaide
-0.81
ership
-0.77
icative
-0.76
idences
-0.75
hips
-0.74
ered
-0.73
places
-0.73
gov
-0.73
POSITIVE LOGITS
Hil
0.81
Robinson
0.80
Maker
0.80
Tire
0.76
Trash
0.73
Wise
0.70
oshenko
0.70
DeV
0.69
Moran
0.68
my
0.68
Activations Density 0.008%