INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.38
1.7%
1870
+0.05
0.2%
30
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.38
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
belliger
-1.06
nukes
-1.01
ruinous
-0.98
demoral
-0.97
massacres
-0.92
ravages
-0.91
armaments
-0.90
disgraceful
-0.90
infuriating
-0.89
traitors
-0.89
POSITIVE LOGITS
<bos>
11.34
GEBURTSDATUM
2.02
expandindo
1.98
Autoritní
1.94
betweenstory
1.82
'\\;'
1.80
تقاوى
1.75
LookAnd
1.72
Italijani
1.67
kasarigan
1.65
Activations Density 0.000%
No Known Activations
This feature has no known activations.