INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.29
1.0%
1870
+0.06
0.2%
1741
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.29
0.00
0
-0.06
0.00
1
-0.06
0.00
Negative Logits
unspeak
-1.64
ruinous
-1.50
ineffec
-1.50
belliger
-1.49
unavoid
-1.45
impractica
-1.37
exasper
-1.37
horrend
-1.35
ineffectual
-1.35
unbear
-1.34
POSITIVE LOGITS
<bos>
9.46
expandindo
1.95
betweenstory
1.85
GEBURTSDATUM
1.76
Италијани
1.72
Administrativna
1.69
Paglinawan
1.65
'\\;'
1.61
Autoritní
1.55
-------------</
1.55
Activations Density 0.000%
No Known Activations
This feature has no known activations.