INDEX
Explanations
phrases related to individuals named Philip
mentions of the name "Philip."
New Auto-Interp
Negative Logits
DERR
-0.78
yrinth
-0.75
bnb
-0.74
LOAD
-0.74
eer
-0.73
ipeg
-0.70
hips
-0.69
EntityItem
-0.68
lly
-0.66
REAM
-0.64
POSITIVE LOGITS
Morris
0.86
Randolph
0.82
son
0.81
anthrop
0.80
osate
0.75
Seymour
0.74
istine
0.74
opol
0.72
entric
0.71
ophe
0.71
Activations Density 0.011%