INDEX
Explanations
information related to news articles and press releases
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.12
0.4%
1870
+0.11
0.3%
1967
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.12
0.04
417
+0.11
0.03
1473
+0.10
0.01
Negative Logits
GeoNames
-0.79
Hvad
-0.73
Preço
-0.71
calciatore
-0.70
hdessä
-0.69
Flere
-0.69
***!
-0.68
GRANTED
-0.67
Eacute
-0.67
Dienstag
-0.66
POSITIVE LOGITS
encomp
1.41
accla
1.34
depic
1.33
intersper
1.33
shenan
1.28
maneu
1.27
volunte
1.24
reluct
1.22
practition
1.21
indestru
1.21
Activations Density 0.145%