INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.36
1.5%
1001
+0.05
0.2%
1964
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.36
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.39
impractica
-1.30
ruinous
-1.29
exasper
-1.25
ineffec
-1.24
belliger
-1.24
unwarran
-1.21
miscon
-1.20
horrend
-1.20
ineffectual
-1.19
POSITIVE LOGITS
<bos>
10.94
GEBURTSDATUM
1.98
expandindo
1.94
betweenstory
1.91
Autoritní
1.79
Италијани
1.71
Administrativna
1.71
Italijani
1.69
Geplaatst
1.65
'\\;'
1.65
Activations Density 0.000%
No Known Activations
This feature has no known activations.