INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.2%
1593
+0.04
0.2%
1150
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.04
0.00
1
-0.04
0.00
Negative Logits
unspeak
-1.55
miscon
-1.31
ruinous
-1.28
ineffec
-1.27
exasper
-1.26
McLaugh
-1.25
belliger
-1.25
odious
-1.21
despotism
-1.18
nukes
-1.17
POSITIVE LOGITS
<bos>
9.53
GEBURTSDATUM
1.75
Autoritní
1.72
betweenstory
1.67
'\\;'
1.65
expandindo
1.60
Administrativna
1.58
LookAnd
1.57
Paglinawan
1.55
дописавши
1.46
Activations Density 0.000%
No Known Activations
This feature has no known activations.