INDEX
Explanations
names, specifically those that are likely to be names of people
the name "Heather" and variations of it in various contexts
New Auto-Interp
Negative Logits
unsub
-0.75
577
-0.73
geon
-0.70
Stars
-0.70
hibition
-0.69
SPONSORED
-0.69
awaru
-0.68
Notable
-0.66
juven
-0.65
culture
-0.65
POSITIVE LOGITS
Loren
1.04
rette
0.96
ottesville
0.88
Heather
0.87
idth
0.75
ewater
0.75
Joy
0.75
aith
0.74
otte
0.74
Dixon
0.74
Activations Density 0.008%