INDEX
Explanations
summaries of information
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.8%
596
+0.10
0.5%
538
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1044
+0.16
0.03
1879
+0.10
0.03
1306
+0.10
0.02
Negative Logits
<bos>
-2.61
ⓧ
-1.03
-1.02
/***
-0.99
<?
-0.96
/**
-0.91
posób
-0.90
<?
-0.85
/*++
-0.77
<>
-0.73
POSITIVE LOGITS
lele
1.30
summary
1.29
thuy
1.28
Summary
1.26
wien
1.25
meis
1.20
myn
1.16
fei
1.13
aen
1.12
SUMMARY
1.12
Activations Density 0.176%