INDEX
Explanations
the name "David" occurring in sentences
mentions of the name "David."
New Auto-Interp
Negative Logits
cffffcc
-0.97
ĺħ
-0.84
¥ŀ
-0.83
tnc
-0.81
mble
-0.81
xual
-0.79
actionGroup
-0.75
NetMessage
-0.74
skirts
-0.70
ãĥ¼ãĥĨ
-0.70
POSITIVE LOGITS
Cameron
0.95
anyahu
0.93
Bowie
0.87
Livingston
0.84
Simon
0.82
Cohen
0.81
Matthews
0.81
Axel
0.80
Koch
0.78
David
0.77
Activations Density 0.014%