INDEX
Explanations
food recipes and associated details
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1699
+0.16
0.5%
906
+0.14
0.4%
599
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
609
+0.16
0.07
382
+0.14
0.06
906
+0.13
-0.00
Negative Logits
astéro
-0.75
Wię
-0.75
więcej
-0.73
Și
-0.72
bardziej
-0.72
Ông
-0.72
Warto
-0.70
Jako
-0.69
distrito
-0.69
Galería
-0.68
POSITIVE LOGITS
noel
1.28
lein
1.26
dispen
1.22
casio
1.22
profi
1.21
edp
1.21
mef
1.21
lara
1.20
afp
1.20
lele
1.19
Activations Density 0.702%