INDEX
Explanations
references to specific products or recommendations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.7%
1005
+0.05
0.2%
807
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1264
+0.16
0.05
1005
+0.05
0.05
515
+0.04
0.04
Negative Logits
<bos>
-2.34
-0.92
ⓧ
-0.91
/**
-0.87
<?
-0.83
<?
-0.79
/***
-0.74
<tfoot>
-0.68
/*++
-0.64
/*
-0.63
POSITIVE LOGITS
bandung
1.00
milano
0.96
maneu
0.95
santiago
0.94
roberto
0.91
lamborghini
0.89
ricardo
0.88
napoli
0.88
maroc
0.87
jorge
0.87
Activations Density 0.071%