INDEX
Explanations
references to a person named "Laura" in various contexts
mentions of the name "Laura."
New Auto-Interp
Negative Logits
cffff
-0.86
rated
-0.79
raged
-0.74
MENTS
-0.72
VALUE
-0.71
fleet
-0.71
hire
-0.71
rified
-0.71
cffffcc
-0.71
nces
-0.68
POSITIVE LOGITS
Palmer
1.03
Jane
0.94
Loren
0.82
Laura
0.82
gdala
0.81
Miller
0.80
Weather
0.79
Joy
0.76
Vo
0.76
uthor
0.74
Activations Density 0.008%