INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.35
1.7%
1870
+0.05
0.3%
1741
+0.05
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.35
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.15
belliger
-1.86
ruinous
-1.84
ineffec
-1.84
horrend
-1.83
disgra
-1.82
exasper
-1.80
odious
-1.73
miscon
-1.72
laug
-1.71
POSITIVE LOGITS
<bos>
12.30
GEBURTSDATUM
2.51
expandindo
2.41
Autoritní
2.21
betweenstory
2.18
kasarigan
2.03
Италијани
2.00
Italijani
1.99
Administrativna
1.96
'\\;'
1.94
Activations Density 0.000%
No Known Activations
This feature has no known activations.