INDEX
Explanations
information related to infections, viruses, and disease spread
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1026
+0.13
0.5%
1624
+0.13
0.5%
537
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
257
+0.13
0.03
1624
+0.13
0.03
765
+0.11
0.02
Negative Logits
priva
-0.58
affez
-0.52
pali
-0.52
aliexpress
-0.49
allarg
-0.48
jira
-0.47
núm
-0.47
Alembic
-0.47
coar
-0.47
芦
-0.47
POSITIVE LOGITS
infection
1.27
infection
1.13
infections
1.12
infected
1.12
infected
1.11
Infection
1.09
infect
1.05
Infection
0.97
Infections
0.96
infect
0.94
Activations Density 0.094%