INDEX
Explanations
mentions of vintage items
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
200
+0.08
0.3%
757
+0.07
0.2%
1222
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
637
+0.08
0.02
932
+0.07
0.02
1113
+0.07
0.02
Negative Logits
ⓧ
-1.05
/**
-0.91
<?
-0.88
-0.85
/*
-0.77
<?
-0.67
<bos>
-0.66
#
-0.63
protected
-0.60
Transcripción
-0.57
POSITIVE LOGITS
vintage
2.24
Vintage
2.08
Vintage
2.02
vintage
2.00
INTAGE
1.48
aen
1.20
antique
1.14
disagre
1.13
maneu
1.13
ftu
1.11
Activations Density 0.129%