INDEX
Explanations
references to locations, organizations, and events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.25
4.1%
1741
+0.06
0.9%
50
+0.04
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
674
+0.25
0.09
108
+0.06
0.43
1713
+0.04
0.55
Negative Logits
despotism
-1.38
belliger
-1.34
massacres
-1.33
Fascism
-1.24
ruinous
-1.24
nukes
-1.21
traitors
-1.20
demoral
-1.19
treachery
-1.16
ineffectual
-1.13
POSITIVE LOGITS
<bos>
17.33
expandindo
2.86
GEBURTSDATUM
2.85
betweenstory
2.79
Administrativna
2.69
تقاوى
2.66
Autoritní
2.65
Italijani
2.50
Италијани
2.50
Мексичка
2.42
Activations Density 0.958%