INDEX
Explanations
references to patterns involving odd and even numbers or related categorical distinctions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.9%
1535
+0.14
0.8%
481
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
481
+0.16
0.02
869
+0.14
0.02
1363
+0.13
0.02
Negative Logits
<bos>
-2.13
angliski
-0.70
}],
-0.69
displayquote
-0.65
},{
-0.62
protected
-0.61
Alguns
-0.61
Tratamiento
-0.60
Skocz
-0.60
PreAuthorize
-0.59
POSITIVE LOGITS
stockholm
1.42
maroc
1.34
jorge
1.34
gettyimages
1.33
maneu
1.27
seoul
1.27
frankfurt
1.26
nicolas
1.24
gabri
1.24
pixabay
1.23
Activations Density 0.045%