INDEX
Explanations
information related to medical conditions, specifically heart attacks and marijuana use
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1581
+0.12
0.4%
1978
+0.11
0.4%
577
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
147
+0.12
0.03
161
+0.11
0.03
1581
+0.10
0.03
Negative Logits
earnestness
-0.65
noblest
-0.59
shenan
-0.59
caprice
-0.59
unspeak
-0.59
poetical
-0.58
liberality
-0.57
Lbs
-0.57
impet
-0.56
unwarran
-0.56
POSITIVE LOGITS
0
0.56
misure
0.56
opzioni
0.55
šech
0.55
regole
0.52
macchine
0.52
applicazioni
0.51
susun
0.51
ínguez
0.50
kristal
0.49
Activations Density 0.109%