INDEX
Explanations
terms related to delivery and shipping processes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.20
1.2%
182
+0.12
0.7%
12
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
80
+0.20
0.02
182
+0.12
0.02
361
+0.12
0.02
Negative Logits
footballers
-1.57
genocide
-1.54
ancestry
-1.52
inheritance
-1.51
nephe
-1.49
amais
-1.49
Į
-1.44
sne
-1.43
ĥ½
-1.41
¨
-1.40
POSITIVE LOGITS
ination
2.27
inates
2.10
inated
2.04
via
2.02
inator
2.02
via
1.87
eer
1.79
onder
1.71
mechanism
1.71
able
1.64
Activations Density 0.141%