INDEX
Explanations
recipes and cooking instructions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2019
+0.27
0.8%
1535
+0.12
0.4%
304
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2019
+0.27
0.03
924
+0.12
0.03
946
+0.10
0.03
Negative Logits
Może
-0.81
Și
-0.71
Gdy
-0.71
Dlaczego
-0.68
Zwar
-0.67
amaged
-0.64
Kiedy
-0.62
Incluso
-0.61
Czym
-0.60
Wię
-0.60
POSITIVE LOGITS
lele
1.40
istan
1.38
hina
1.31
embra
1.30
dispen
1.26
mef
1.26
salu
1.23
ordina
1.23
hej
1.23
alkoh
1.20
Activations Density 0.055%