INDEX
Explanations
information related to nonprofit organizations and donations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.22
0.7%
878
+0.08
0.3%
1042
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
19
+0.22
0.04
126
+0.08
0.04
771
+0.06
0.03
Negative Logits
<bos>
-2.67
esternos
-0.69
AddField
-0.62
SequentialGroup
-0.60
RemoveField
-0.60
intios
-0.59
attend
-0.59
arrive
-0.58
echo
-0.58
Дер
-0.58
POSITIVE LOGITS
Juf
1.72
Khart
1.54
Momb
1.46
eiffel
1.45
panama
1.44
wien
1.43
squa
1.42
lara
1.42
maneu
1.41
Keny
1.40
Activations Density 0.303%