INDEX
Explanations
proper names, specifically the name "Melissa"
the presence of the name "Melissa" and its variations
New Auto-Interp
Negative Logits
*/(
-0.90
arist
-0.85
yrinth
-0.79
raged
-0.74
redo
-0.70
gers
-0.70
ãĤĮ
-0.69
gres
-0.68
uned
-0.68
stroke
-0.68
POSITIVE LOGITS
Melissa
0.98
ILCS
0.94
Pixel
0.74
Ether
0.72
Loren
0.71
Briggs
0.70
Patricia
0.69
Islands
0.69
lettuce
0.69
Garcia
0.67
Activations Density 0.012%