INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.5%
1870
+0.06
0.3%
1253
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
belliger
-0.97
demoral
-0.97
traitors
-0.93
nukes
-0.91
massacres
-0.91
ineffectual
-0.91
ruinous
-0.90
infuriating
-0.90
disgraceful
-0.89
infuri
-0.89
POSITIVE LOGITS
<bos>
11.80
GEBURTSDATUM
2.36
expandindo
2.26
Autoritní
2.10
betweenstory
1.92
'\\;'
1.85
تقاوى
1.82
Geplaatst
1.82
Administrativna
1.80
Италијани
1.78
Activations Density 0.000%
No Known Activations
This feature has no known activations.