INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.22
0.7%
1490
+0.06
0.2%
1848
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.22
0.00
0
-0.06
0.00
1
-0.06
0.00
Negative Logits
reluct
-3.26
impra
-3.23
unspeak
-3.19
shenan
-3.15
disagre
-3.02
increa
-2.91
impractica
-2.90
indestru
-2.85
disgra
-2.84
depic
-2.79
POSITIVE LOGITS
<bos>
7.57
GEBURTSDATUM
1.75
expandindo
1.66
للاسماء
1.60
betweenstory
1.58
'\\;'
1.57
Administrativna
1.55
setVerticalGroup
1.49
Walkover
1.48
Италијани
1.48
Activations Density 0.000%
No Known Activations
This feature has no known activations.