INDEX
Explanations
instances of conditional statements, specifically those starting with "if"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.25
1.6%
1265
+0.13
0.8%
404
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
404
+0.25
0.09
1265
+0.13
0.07
757
+0.12
0.07
Negative Logits
<bos>
-3.36
ⓧ
-1.01
<?
-0.91
-0.78
Vegeu
-0.73
Enllaços
-0.69
/**
-0.67
///**
-0.62
<?
-0.61
HasAnnotation
-0.61
POSITIVE LOGITS
stockholm
1.22
accla
1.17
wien
1.16
Confe
1.15
maneu
1.15
eiffel
1.14
inev
1.14
jacques
1.14
Manufact
1.13
disgra
1.11
Activations Density 0.233%