INDEX
Explanations
phrases related to healthcare policy in a legislative context
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1120
+0.10
0.3%
802
+0.09
0.2%
939
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
939
+0.10
0.05
802
+0.09
0.04
1499
+0.08
0.05
Negative Logits
indestru
-0.82
guarante
-0.77
stickied
-0.75
encomp
-0.74
Mlle
-0.74
circums
-0.74
aussitôt
-0.74
Secre
-0.73
hentai
-0.73
depic
-0.73
POSITIVE LOGITS
transition
0.88
transition
0.81
Transition
0.75
Transition
0.74
transitioning
0.68
transitions
0.66
gradually
0.64
replacement
0.63
transitioned
0.62
transitional
0.62
Activations Density 0.486%