INDEX
Explanations
references to regulations, commerce, and government trade
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
663
+0.18
0.7%
1870
+0.14
0.5%
313
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
663
+0.18
0.02
1407
+0.14
0.02
313
+0.13
0.02
Negative Logits
solidar
-0.59
concier
-0.54
superintend
-0.53
disbur
-0.52
ausp
-0.51
sovere
-0.50
bermuda
-0.49
Parla
-0.49
Rodin
-0.48
bapt
-0.48
POSITIVE LOGITS
Commerce
1.18
commerce
1.15
commerce
1.10
Commerce
1.07
COMMERCE
0.98
merchant
0.81
merchants
0.79
MERCE
0.72
Merchant
0.72
Merchants
0.71
Activations Density 0.078%