INDEX
Neuron Alignment
Index
Value
% of L₁
156
+0.26
1.5%
369
+0.14
0.8%
173
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
173
+0.26
0.02
382
+0.14
0.02
271
+0.13
0.01
Negative Logits
woke
-1.55
ĥ½
-1.53
yours
-1.49
childhood
-1.49
fatal
-1.44
kay
-1.38
your
-1.37
mid
-1.36
scrolling
-1.35
ayed
-1.33
POSITIVE LOGITS
abad
1.93
chen
1.75
erals
1.69
fors
1.58
elines
1.58
Electronics
1.57
lectual
1.56
itol
1.56
ings
1.53
itic
1.52
Activations Density 0.022%