INDEX
Explanations
proper names, specifically the name "Alan"
mentions of the name "Alan."
New Auto-Interp
Negative Logits
gerald
-0.85
ODUCT
-0.80
ledged
-0.78
LINE
-0.75
lyak
-0.74
dds
-0.74
ippi
-0.74
Roaming
-0.74
stakes
-0.73
KI
-0.72
POSITIVE LOGITS
Turing
1.09
Lev
0.82
Watts
0.82
Gross
0.80
tering
0.78
Boyle
0.78
ization
0.78
isher
0.76
Shepard
0.76
Moore
0.75
Activations Density 0.022%