INDEX
Explanations
contact and location information, potentially on websites
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.16
0.6%
1343
+0.07
0.3%
1804
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.16
0.03
1390
+0.07
0.03
1419
+0.06
0.03
Negative Logits
<bos>
-1.10
/**
-1.00
ⓧ
-0.96
<?
-0.91
/***
-0.90
<?
-0.89
quitted
-0.89
-0.81
///**
-0.77
/*
-0.77
POSITIVE LOGITS
montagna
0.61
تضيفلها
0.59
pioggia
0.57
Karang
0.55
spiaggia
0.55
expédi
0.54
Sardegna
0.53
Banjar
0.53
dropna
0.52
déliv
0.51
Activations Density 0.069%