INDEX
Explanations
biographical information related to individuals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.08
0.3%
1467
+0.06
0.2%
1935
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1385
+0.08
0.09
1935
+0.06
0.05
1671
+0.05
0.05
Negative Logits
-1.04
ⓧ
-0.93
<?
-0.86
/**
-0.84
/*
-0.82
<?
-0.79
/***
-0.76
///**
-0.74
//{
-0.72
}{||-0.67
POSITIVE LOGITS
affor
1.77
increa
1.77
stockholm
1.73
impra
1.69
accla
1.62
maneu
1.61
lidl
1.58
strick
1.58
inev
1.56
fortn
1.55
Activations Density 0.931%