INDEX
Explanations
occurrences of the word "advances" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
376
+0.17
1.0%
125
+0.12
0.7%
290
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
159
+0.17
0.01
267
+0.12
0.01
125
+0.12
0.01
Negative Logits
athing
-1.80
lest
-1.75
TY
-1.75
ubicin
-1.73
zos
-1.61
keit
-1.59
unes
-1.59
Copyright
-1.52
akia
-1.52
yan
-1.48
POSITIVE LOGITS
Ĺ
2.36
ħ
2.29
ī
2.26
ļ
2.23
Ĩ
2.18
Ī
2.17
ķ
2.11
Ķ
2.10
ĩ
2.09
ģ
2.08
Activations Density 0.008%