INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.31
1.2%
1870
+0.07
0.3%
1253
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.31
0.00
0
-0.07
0.00
1
-0.05
0.00
Negative Logits
massacres
-0.93
belliger
-0.90
only
-0.87
despotism
-0.87
ravages
-0.83
ruinous
-0.83
ineffectual
-0.82
totalitarian
-0.82
repressive
-0.81
not
-0.81
POSITIVE LOGITS
<bos>
10.59
expandindo
2.19
GEBURTSDATUM
2.07
betweenstory
1.77
'\\;'
1.77
Италијани
1.74
Autoritní
1.70
autorytatywna
1.65
resourceCulture
1.63
Administrativna
1.61
Activations Density 0.000%
No Known Activations
This feature has no known activations.