INDEX
Explanations
financial figures and values
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.23
0.8%
1343
+0.08
0.3%
446
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1419
+0.23
0.03
801
+0.08
0.03
446
+0.07
0.02
Negative Logits
<bos>
-1.40
<?
-0.72
ⓧ
-0.66
Personendaten
-0.65
/***
-0.58
endwhile
-0.57
academia
-0.56
queryInterface
-0.56
{?>-0.55
///**
-0.55
POSITIVE LOGITS
Minang
1.10
doña
1.04
Darío
1.04
santiago
0.92
Bahía
0.90
Áng
0.89
Lucía
0.88
Asunción
0.86
Almería
0.86
jawa
0.86
Activations Density 0.093%