INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.30
1.3%
1870
+0.09
0.4%
1253
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.30
0.00
0
-0.09
0.00
1
-0.09
0.00
Negative Logits
belliger
-1.22
nukes
-1.03
ruinous
-1.03
despotism
-1.03
mutiny
-0.99
desertion
-0.98
massacres
-0.96
scound
-0.95
unlaw
-0.95
tyrants
-0.94
POSITIVE LOGITS
<bos>
11.10
GEBURTSDATUM
2.08
expandindo
2.04
betweenstory
1.93
تقاوى
1.73
Autoritní
1.69
'\\;'
1.68
Italijani
1.62
Geplaatst
1.61
Administrativna
1.61
Activations Density 0.000%
No Known Activations
This feature has no known activations.