INDEX
Explanations
instances of the name "Cooper"
mentions of the name "Cooper."
New Auto-Interp
Negative Logits
Magikarp
-0.63
soever
-0.63
rely
-0.63
eric
-0.63
rooms
-0.62
chal
-0.61
seeing
-0.60
enic
-0.59
fix
-0.58
-0.58
POSITIVE LOGITS
atives
1.00
stown
0.95
Cooper
0.93
ately
0.92
icker
0.85
atively
0.84
ATURE
0.84
ature
0.81
lear
0.81
ords
0.81
Activations Density 0.020%