INDEX
Explanations
proper nouns representing people with the surname "Phillips."
the mentions of the name "Phillips."
New Auto-Interp
Negative Logits
ERAL
-0.89
joined
-0.76
venge
-0.70
hibition
-0.70
Bihar
-0.69
juven
-0.68
izen
-0.66
fy
-0.66
quo
-0.65
HCR
-0.64
POSITIVE LOGITS
Phillips
1.12
Parsons
0.92
pie
0.79
arella
0.77
cones
0.76
sey
0.75
screws
0.74
atta
0.74
worth
0.73
nuts
0.73
Activations Density 0.007%