INDEX
Explanations
references to citizens' rights and protections
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.30
1.1%
872
+0.12
0.4%
1352
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
872
+0.30
0.08
1380
+0.12
0.04
764
+0.07
0.03
Negative Logits
<bos>
-2.38
ratify
-0.69
<!--
-0.64
reunite
-0.63
disbur
-0.62
SourceChecksum
-0.61
inaugurate
-0.60
rehabilitate
-0.60
tagHelperRunner
-0.58
finalize
-0.57
POSITIVE LOGITS
palio
1.12
prado
1.02
pican
1.01
paradiso
1.00
milano
0.99
santiago
0.96
bandung
0.94
rancho
0.93
Minang
0.92
teresa
0.91
Activations Density 0.918%