INDEX
Explanations
references to various types of alcoholic beverages and related information like pricing and packaging options
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1150
+0.21
0.6%
1510
+0.17
0.5%
1343
+0.16
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1510
+0.21
0.04
1150
+0.17
0.03
1343
+0.16
0.05
Negative Logits
Eksteraj
-0.74
Glej
-0.74
Przyp
-0.72
astéro
-0.70
Kaip
-0.69
Legături
-0.69
Dlaczego
-0.67
Apesar
-0.67
muchas
-0.66
Czym
-0.65
POSITIVE LOGITS
";"
0.80
idr
0.78
labd
0.78
)
0.78
"|"
0.75
|]
0.75
fch
0.74
saar
0.73
stratigraph
0.73
prodi
0.73
Activations Density 0.180%