INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.35
1.9%
1870
+0.06
0.3%
1741
+0.05
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.35
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.87
belliger
-1.78
ineffec
-1.76
horrend
-1.71
laug
-1.67
unlaw
-1.66
miscon
-1.62
ruinous
-1.61
disgra
-1.59
impractica
-1.54
POSITIVE LOGITS
<bos>
12.72
GEBURTSDATUM
2.73
betweenstory
2.49
expandindo
2.47
Autoritní
2.46
kasarigan
2.19
Administrativna
2.14
Geplaatst
2.14
تقاوى
2.13
'\\;'
2.10
Activations Density 0.000%
No Known Activations
This feature has no known activations.