INDEX
Explanations
specific attributes or qualities associated with objects and actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.33
1.9%
23
+0.19
1.1%
271
+0.15
0.9%
Correlated Neurons
Index
P. Corr.
Cos Sim.
156
+0.33
0.17
271
+0.19
-0.06
116
+0.15
0.09
Negative Logits
jan
-1.43
Rptr
-1.41
Ct
-1.39
emente
-1.39
izione
-1.36
ei
-1.34
si
-1.32
amente
-1.30
siRNA
-1.29
kowski
-1.29
POSITIVE LOGITS
·
2.20
ľ
2.11
Ĺ
2.07
İ
1.93
µ
1.92
²
1.84
IJ
1.84
ħ
1.83
ij
1.81
Īĺ
1.81
Activations Density 4.553%