INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.21
0.6%
755
+0.05
0.2%
1601
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.21
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
unspeak
-0.94
despotism
-0.87
ennemi
-0.85
unlaw
-0.84
Byp
-0.83
impractica
-0.82
unwarran
-0.82
disgra
-0.82
ingrat
-0.81
downvoted
-0.81
POSITIVE LOGITS
<bos>
7.04
Autoritní
1.16
GraphicsUnit
1.11
GEBURTSDATUM
1.08
kasarigan
1.07
AddTagHelper
1.04
expandindo
1.02
transQ
1.00
'\\;'
1.00
Италијани
0.97
Activations Density 0.000%
No Known Activations
This feature has no known activations.