INDEX
Explanations
statements related to legal matters, copyright information, and publication guidelines
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.21
0.8%
1343
+0.11
0.4%
198
+0.08
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
193
+0.21
0.04
198
+0.11
0.04
1851
+0.08
0.03
Negative Logits
<bos>
-1.51
ⓧ
-1.07
-1.06
/**
-1.01
<?
-0.97
/*
-0.87
Transcripción
-0.70
/***
-0.70
/*!
-0.66
springfox
-0.64
POSITIVE LOGITS
saar
1.01
stockholm
0.99
pioggia
0.97
jaya
0.97
mezza
0.93
umbre
0.91
allah
0.90
cartier
0.89
franz
0.89
cammin
0.87
Activations Density 0.091%