INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.41
2.4%
381
+0.06
0.4%
1741
+0.05
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.41
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.72
reluct
-2.71
disgra
-2.68
unlaw
-2.67
unwarran
-2.60
impractica
-2.59
disagre
-2.57
impra
-2.51
shenan
-2.48
indestru
-2.46
POSITIVE LOGITS
<bos>
13.46
GEBURTSDATUM
2.11
expandindo
2.10
betweenstory
2.07
Autoritní
2.01
تقاوى
2.00
Administrativna
1.87
Italijani
1.82
kaarangay
1.81
Италијани
1.78
Activations Density 0.000%
No Known Activations
This feature has no known activations.