INDEX
Explanations
references to entities or names related to "Cooper."
mentions of the name "Cooper."
New Auto-Interp
Negative Logits
IAS
-0.67
rely
-0.65
chal
-0.65
enic
-0.65
eric
-0.64
seeing
-0.64
anamo
-0.61
Magikarp
-0.61
los
-0.59
untled
-0.59
POSITIVE LOGITS
Cooper
1.04
stown
1.03
atives
0.98
icker
0.88
ately
0.87
ATURE
0.87
Draper
0.86
lear
0.81
ature
0.81
ords
0.81
Activations Density 0.014%