INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.35
1.7%
1870
+0.06
0.3%
381
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.35
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
massacres
-0.90
belliger
-0.89
despotism
-0.88
traitors
-0.88
ruinous
-0.82
ineffectual
-0.80
communists
-0.80
demoral
-0.79
nukes
-0.79
treachery
-0.77
POSITIVE LOGITS
<bos>
11.92
GEBURTSDATUM
2.18
expandindo
2.13
Autoritní
2.00
betweenstory
1.87
تقاوى
1.78
kaarangay
1.73
kasarigan
1.72
Geplaatst
1.71
Италијани
1.70
Activations Density 0.000%
No Known Activations
This feature has no known activations.