INDEX
Explanations
references to a specific brand of beer
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
410
+0.17
0.8%
893
+0.13
0.6%
90
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
410
+0.17
0.02
314
+0.13
0.02
1276
+0.13
0.02
Negative Logits
徨
-0.49
mxArray
-0.46
getLastName
-0.46
Dempsey
-0.45
course
-0.44
Override
-0.43
getFirstName
-0.42
Xylene
-0.42
=""/>
-0.42
Contrato
-0.41
POSITIVE LOGITS
Bud
1.54
BUD
1.50
Bud
1.39
bud
1.31
bud
1.20
BUD
1.20
Buds
1.18
Budd
1.14
buds
1.03
paff
0.97
Activations Density 0.127%