INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.28
1.1%
1870
+0.05
0.2%
1741
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.28
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
ruinous
-1.20
belliger
-1.10
demoral
-1.05
ineffectual
-1.05
odious
-1.02
miscon
-1.00
in
-1.00
despotism
-0.98
cowards
-0.98
impotent
-0.96
POSITIVE LOGITS
<bos>
9.95
expandindo
2.30
GEBURTSDATUM
2.12
kasarigan
2.01
Autoritní
1.87
affez
1.69
LookAnd
1.68
parteci
1.68
sappi
1.68
appunt
1.68
Activations Density 0.000%
No Known Activations
This feature has no known activations.