INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.30
1.1%
468
+0.05
0.2%
1253
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.30
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
reluct
-6.62
shenan
-6.42
impra
-6.38
unspeak
-6.29
increa
-6.20
disagre
-6.16
depic
-6.14
encomp
-5.94
apprehen
-5.90
maneu
-5.87
POSITIVE LOGITS
<bos>
11.40
Walkover
3.10
GEBURTSDATUM
2.90
Paglinawan
2.86
Autoritní
2.77
expandindo
2.71
betweenstory
2.71
'\\;'
2.64
Administrativna
2.63
Himo
2.60
Activations Density 0.000%
No Known Activations
This feature has no known activations.