INDEX
Explanations
phrases related to a specific name "Alan"
mentions of the name "Alan."
New Auto-Interp
Negative Logits
anim
-0.88
ledged
-0.74
gerald
-0.72
ODUCT
-0.68
LED
-0.66
eous
-0.65
xual
-0.65
cific
-0.64
dds
-0.64
ever
-0.63
POSITIVE LOGITS
Turing
1.10
Watts
0.87
Kurd
0.82
Greens
0.80
isen
0.80
ization
0.77
Boyle
0.77
Gross
0.77
Wake
0.77
izing
0.77
Activations Density 0.023%