INDEX
Explanations
legal terms and phrases related to court cases and rulings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.19
0.7%
453
+0.09
0.3%
1379
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1499
+0.19
0.02
1343
+0.09
0.01
1150
+0.07
0.01
Negative Logits
<bos>
-2.37
ⓧ
-1.12
/**
-0.94
<?
-0.84
-0.82
<?
-0.67
/***
-0.64
/*
-0.61
disbur
-0.58
Transcripción
-0.57
POSITIVE LOGITS
épu
0.69
maroc
0.68
↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
0.65
soulign
0.65
véhic
0.64
vokal
0.63
kristal
0.63
seksi
0.63
↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
0.63
karet
0.63
Activations Density 0.024%