INDEX
Explanations
sequences of numbers, potentially related to a specific pattern or code
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.18
1.0%
1978
+0.12
0.7%
382
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1978
+0.18
0.15
382
+0.12
0.12
478
+0.11
-0.00
Negative Logits
<bos>
-2.19
ⓧ
-0.94
/*
-0.80
/**
-0.80
-0.78
/*++
-0.74
<?
-0.73
,
-0.71
continue
-0.70
put
-0.69
POSITIVE LOGITS
affor
2.33
maneu
2.27
increa
2.25
impra
2.01
inev
2.01
perfet
1.96
stockholm
1.95
accla
1.93
disagre
1.93
effe
1.91
Activations Density 0.453%