INDEX
Explanations
the name "Tommy" in various contexts
New Auto-Interp
Negative Logits
hips
-0.86
iard
-0.84
places
-0.82
eer
-0.79
ered
-0.78
ership
-0.78
ortment
-0.76
hip
-0.75
ividual
-0.75
Ĥİ
-0.75
POSITIVE LOGITS
Hil
0.89
Robinson
0.86
oshenko
0.82
Trash
0.80
kn
0.76
Caldwell
0.75
Bone
0.74
Wise
0.74
Tune
0.72
Tire
0.72
Activations Density 0.022%