INDEX
Explanations
references to technology and technical details
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1937
+0.16
0.7%
1096
+0.16
0.7%
1323
+0.14
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1096
+0.16
0.03
1323
+0.16
0.02
1491
+0.14
0.02
Negative Logits
lanzen
-0.52
artamentos
-0.48
zvuky
-0.46
ganu
-0.43
piłkarz
-0.42
bolista
-0.42
lusst
-0.42
cookies
-0.42
tycker
-0.41
יצד
-0.41
POSITIVE LOGITS
Ser
1.18
Ser
1.09
ser
1.08
SER
1.03
serials
1.01
sergio
1.00
Serial
0.99
serial
0.94
Sermons
0.93
exé
0.92
Activations Density 0.132%