INDEX
Explanations
phrases describing events or settings in a story, particularly with a mysterious or fantasy vibe
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
964
+0.10
0.3%
297
+0.08
0.2%
1135
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
453
+0.10
0.07
297
+0.08
0.06
682
+0.08
0.04
Negative Logits
انيف
-0.58
xxvi
-0.57
xxv
-0.55
xxiii
-0.55
pinulongan
-0.55
HtmlAttribute
-0.53
xxii
-0.53
IUrlHelper
-0.52
ImageContext
-0.50
xxiv
-0.50
POSITIVE LOGITS
initial
1.11
initial
0.96
inicial
0.95
Initial
0.94
Initial
0.93
initially
0.88
first
0.86
starting
0.86
earliest
0.82
early
0.82
Activations Density 1.273%