INDEX
Explanations
mentions of a particular person named Andy with a high level of activation, potentially indicating a strong association with this individual
mentions of the name "Andy."
New Auto-Interp
Negative Logits
maid
-0.81
hips
-0.78
ingen
-0.77
sole
-0.72
nces
-0.71
document
-0.70
Demand
-0.70
ngth
-0.69
inals
-0.68
cens
-0.68
POSITIVE LOGITS
Andy
0.98
Dalton
0.87
aimon
0.79
Andy
0.78
Neil
0.77
Neal
0.74
Cohen
0.71
visors
0.70
Pa
0.68
Alexander
0.68
Activations Density 0.004%