INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.28
1.0%
1323
+0.06
0.2%
406
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.28
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.71
horrend
-1.52
ruinous
-1.46
exasper
-1.43
laug
-1.39
miscon
-1.38
ineffec
-1.35
disgra
-1.34
odious
-1.34
demoral
-1.31
POSITIVE LOGITS
<bos>
9.63
GEBURTSDATUM
2.14
Autoritní
2.02
expandindo
1.88
autorytatywna
1.79
'\\;'
1.75
betweenstory
1.71
Himo
1.70
Administrativna
1.67
Walkover
1.66
Activations Density 0.000%
No Known Activations
This feature has no known activations.