INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.27
0.9%
1256
+0.05
0.2%
1235
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.27
0.00
0
-0.05
0.00
1
-0.04
0.00
Negative Logits
reluct
-6.72
shenan
-6.47
impra
-6.44
increa
-6.25
depic
-6.17
unspeak
-6.14
disagre
-6.10
maneu
-6.03
encomp
-5.96
indestru
-5.81
POSITIVE LOGITS
<bos>
9.86
Walkover
3.00
Paglinawan
2.65
GEBURTSDATUM
2.62
betweenstory
2.62
Himo
2.59
'\\;'
2.50
-------------</
2.47
Panamoan
2.47
SharedDtor
2.44
Activations Density 0.000%
No Known Activations
This feature has no known activations.