INDEX
Explanations
references to characters and story elements related to phantoms
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
277
+0.13
0.7%
82
+0.13
0.7%
467
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
277
+0.13
0.02
56
+0.13
-0.00
379
+0.13
0.02
Negative Logits
´
-2.17
ĻĤ
-2.01
²
-1.95
±
-1.95
µ
-1.83
·
-1.80
°
-1.72
Ŀ
-1.71
Īĺ
-1.69
£
-1.67
POSITIVE LOGITS
less
2.27
ful
1.62
lessness
1.52
thrill
1.51
axel
1.51
quez
1.50
fully
1.45
wagen
1.43
nell
1.41
://
1.40
Activations Density 7.791%