INDEX
Explanations
the name "Marcus" with varying intensities
instances of the name "Marcus."
New Auto-Interp
Negative Logits
boarding
-0.91
eer
-0.77
board
-0.75
saf
-0.74
eared
-0.72
ships
-0.72
ship
-0.71
eering
-0.70
bare
-0.69
icial
-0.68
POSITIVE LOGITS
Aure
1.16
Marcus
1.01
ias
0.85
Marcus
0.83
Curtis
0.80
ius
0.79
Fuller
0.75
Fen
0.75
Mari
0.75
Dixon
0.75
Activations Density 0.009%