INDEX
Explanations
proper nouns related to the name "Philip"
occurrences of the name "Philip."
New Auto-Interp
Negative Logits
bnb
-0.82
egal
-0.76
eer
-0.75
DERR
-0.75
cession
-0.73
yrinth
-0.72
cial
-0.70
lly
-0.70
hips
-0.69
termination
-0.66
POSITIVE LOGITS
Randolph
0.92
Morris
0.84
Seymour
0.79
son
0.77
Wad
0.73
entric
0.72
osate
0.70
anthrop
0.70
Pull
0.69
lectic
0.68
Activations Density 0.014%