INDEX
Explanations
information related to events or conferences, including their scheduling and locations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.27
1.0%
856
+0.11
0.4%
1013
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
548
+0.27
0.06
1343
+0.11
0.06
1453
+0.09
0.05
Negative Logits
<bos>
-2.17
ⓧ
-0.79
/**
-0.70
-0.70
/*
-0.68
<?
-0.67
<?
-0.65
}{||-0.61
/***
-0.61
MenuView
-0.59
POSITIVE LOGITS
maneu
1.08
catég
1.05
beverly
1.02
leonardo
1.01
bayern
0.98
hcm
0.97
blackpink
0.96
délib
0.95
épu
0.94
lara
0.94
Activations Density 0.188%