INDEX
Explanations
words related to quarantine and isolation
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1677
+0.13
0.5%
1187
+0.13
0.5%
1557
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
860
+0.13
0.02
1677
+0.13
0.02
1557
+0.11
0.02
Negative Logits
felipe
-0.72
cristina
-0.71
sergio
-0.71
javier
-0.69
Sinal
-0.67
Minang
-0.67
dedans
-0.67
Cak
-0.66
chrétien
-0.64
Áng
-0.64
POSITIVE LOGITS
isolation
1.31
isolate
1.26
Isolation
1.21
isolating
1.17
isolation
1.17
Isolation
1.17
isolated
1.15
isolated
1.14
isolates
1.09
isolate
1.09
Activations Density 0.079%