INDEX
Explanations
phrases indicating a need for action or separate items within a list
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.18
0.9%
976
+0.11
0.5%
860
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
860
+0.18
0.03
976
+0.11
0.03
347
+0.11
0.03
Negative Logits
<bos>
-2.98
ⓧ
-0.82
<?
-0.78
/**
-0.72
<?
-0.71
/*!
-0.68
/***
-0.67
//{
-0.64
Enllaços
-0.59
HasIndex
-0.59
POSITIVE LOGITS
stockholm
1.58
frankfurt
1.44
Juf
1.43
wien
1.42
thut
1.41
fep
1.35
aen
1.32
fta
1.31
eiffel
1.31
Confu
1.31
Activations Density 0.151%