INDEX
Explanations
mentions of a person named "Danny" with increasing levels of activation
mentions of the name "Danny."
New Auto-Interp
Negative Logits
sburgh
-1.02
sites
-0.84
atcher
-0.79
totality
-0.70
ËĪ
-0.67
orship
-0.67
ament
-0.67
nir
-0.67
itude
-0.66
atches
-0.65
POSITIVE LOGITS
DeV
0.97
Amend
0.93
Glover
0.88
Meyer
0.81
Hamilton
0.80
Elf
0.78
Boyle
0.76
Sullivan
0.70
Chau
0.70
Barron
0.69
Activations Density 0.023%