INDEX
Explanations
mentions of the name "Michelle"
mentions of the name "Michelle."
New Auto-Interp
Negative Logits
flat
-0.74
ition
-0.71
ngth
-0.69
een
-0.69
fare
-0.68
alion
-0.66
tions
-0.66
ĵĺ
-0.65
âĶĢâĶĢ
-0.65
etheless
-0.65
POSITIVE LOGITS
Dug
0.98
Malk
0.88
Bach
0.87
Obama
0.82
Wan
0.80
Michelle
0.79
Obama
0.78
Alexander
0.76
Dock
0.75
Vis
0.74
Activations Density 0.032%