INDEX
Explanations
proper nouns, specifically the name "David"
references to the name "David."
New Auto-Interp
Negative Logits
cffffcc
-1.04
ĺħ
-0.83
NetMessage
-0.81
¥ŀ
-0.80
tnc
-0.76
suscept
-0.75
isites
-0.75
actionGroup
-0.74
mble
-0.73
xual
-0.72
POSITIVE LOGITS
Bowie
1.01
Cameron
0.95
Axel
0.92
Wallace
0.91
anyahu
0.90
Beckham
0.87
son
0.86
Simon
0.85
Cohen
0.82
Barton
0.82
Activations Density 0.018%