INDEX
Explanations
mentions of documentaries and related terms
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1325
+0.16
0.6%
1870
+0.12
0.5%
1310
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1325
+0.16
0.02
699
+0.12
0.02
1310
+0.11
0.02
Negative Logits
Ethylbenzene
-0.50
pexpr
-0.48
Tracce
-0.48
المراجع
-0.48
Abp
-0.47
pegno
-0.47
AnchorStyles
-0.44
Heft
-0.44
ژاد
-0.44
rån
-0.44
POSITIVE LOGITS
doc
1.18
Doc
1.17
documentation
1.14
apprehen
1.09
Documentary
1.05
Documentation
1.04
docs
1.04
documenting
1.03
document
1.03
Doc
1.02
Activations Density 0.058%