INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.24
0.7%
1741
+0.07
0.2%
617
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.24
0.00
0
-0.07
0.00
1
-0.05
0.00
Negative Logits
belliger
-1.66
unspeak
-1.62
horrend
-1.62
laug
-1.50
unavoid
-1.47
disgra
-1.47
ineffec
-1.45
subver
-1.38
wilfully
-1.34
miscon
-1.33
POSITIVE LOGITS
<bos>
7.77
GEBURTSDATUM
1.86
expandindo
1.76
Autoritní
1.60
-------------</
1.59
kasarigan
1.58
betweenstory
1.56
'\\;'
1.53
EndGlobalSection
1.47
îna
1.44
Activations Density 0.000%
No Known Activations
This feature has no known activations.