INDEX
Explanations
references to the name "Watson."
references to a specific individual named Watson
New Auto-Interp
Negative Logits
amera
-0.84
ulatory
-0.82
ĩ
-0.77
nect
-0.71
uation
-0.70
wives
-0.69
eways
-0.68
fertile
-0.67
uate
-0.67
egal
-0.66
POSITIVE LOGITS
atson
1.01
Watson
0.99
Holmes
0.92
combe
0.84
ITH
0.82
Phill
0.77
orld
0.77
ingly
0.74
bley
0.74
ITNESS
0.74
Activations Density 0.057%