INDEX
Explanations
names of people or entities, particularly focusing on the surname "Phillips"
occurrences of the name "Phillips."
New Auto-Interp
Negative Logits
ERAL
-0.76
fy
-0.74
hibition
-0.73
gary
-0.72
clud
-0.71
quo
-0.70
ctors
-0.69
rous
-0.68
think
-0.68
ilty
-0.68
POSITIVE LOGITS
ippi
1.01
Lovecraft
0.92
ussen
0.91
hift
0.79
sey
0.77
atile
0.77
pie
0.75
Parsons
0.72
=-=-
0.71
ipher
0.70
Activations Density 0.032%