INDEX
Explanations
news articles related to legal cases or disputes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2019
+0.37
1.3%
1535
+0.25
0.9%
304
+0.17
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2019
+0.37
0.10
1535
+0.25
0.09
1445
+0.17
0.09
Negative Logits
tupperware
-0.96
Darum
-0.89
geforce
-0.83
teflon
-0.81
Może
-0.81
Czym
-0.79
VOOR
-0.79
BORROW
-0.77
Zwar
-0.77
explications
-0.77
POSITIVE LOGITS
istan
0.88
Coim
0.85
Descrip
0.82
antik
0.79
Dimen
0.79
haba
0.79
optik
0.78
Keny
0.77
hina
0.77
harap
0.75
Activations Density 0.393%