INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.4%
1870
+0.06
0.3%
468
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.06
0.00
1
-0.04
0.00
Negative Logits
unspeak
-1.67
belliger
-1.51
ruinous
-1.48
horrend
-1.46
ineffec
-1.43
laug
-1.41
exasper
-1.39
odious
-1.38
miscon
-1.37
ineffectual
-1.36
POSITIVE LOGITS
<bos>
11.29
GEBURTSDATUM
2.35
expandindo
2.15
Autoritní
2.09
betweenstory
2.02
'\\;'
1.99
kasarigan
1.91
Administrativna
1.86
Италијани
1.86
Italijani
1.85
Activations Density 0.000%
No Known Activations
This feature has no known activations.