INDEX
Explanations
the word "anything" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.25
1.3%
1984
+0.12
0.6%
1296
+0.12
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
971
+0.25
0.04
1335
+0.12
0.04
1811
+0.12
0.03
Negative Logits
<bos>
-2.67
ⓧ
-0.87
/*
-0.81
-0.75
/***
-0.71
#![
-0.66
/**
-0.66
<?
-0.64
Таким
-0.57
$_['
-0.56
POSITIVE LOGITS
riva
1.31
lele
1.30
maroc
1.30
Czechos
1.25
tramont
1.25
riviera
1.19
bandung
1.19
ANYTHING
1.18
kokos
1.14
silikon
1.11
Activations Density 0.038%