INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.35
1.5%
1120
+0.05
0.2%
344
+0.05
0.2%
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
-1.82
belliger
-1.60
disgra
-1.59
unlaw
-1.54
ruinous
-1.48
exasper
-1.47
miscon
-1.45
ineffec
-1.43
reluct
-1.40
impractica
-1.38
POSITIVE LOGITS
<bos>
11.39
GEBURTSDATUM
2.07
expandindo
2.00
betweenstory
1.94
تقاوى
1.83
'\\;'
1.82
Autoritní
1.81
Administrativna
1.76
Paglinawan
1.73
kasarigan
1.71
Activations Density 0.000%
No Known Activations
This feature has no known activations.