INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.37
2.1%
381
+0.06
0.3%
1870
+0.05
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.37
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.96
disgra
-1.75
belliger
-1.74
unlaw
-1.74
ineffec
-1.72
horrend
-1.71
impractica
-1.66
exasper
-1.64
ruinous
-1.63
McLaugh
-1.62
POSITIVE LOGITS
<bos>
12.88
GEBURTSDATUM
2.54
expandindo
2.34
betweenstory
2.30
Autoritní
2.23
تقاوى
2.04
'\\;'
1.99
Administrativna
1.99
LookAnd
1.96
Италијани
1.93
Activations Density 0.000%
No Known Activations
This feature has no known activations.