INDEX
Explanations
words related to medical conditions and the concept of absence or deficiency
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
164
+0.15
0.9%
115
+0.14
0.8%
499
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
426
+0.15
0.01
499
+0.14
0.01
39
+0.11
0.01
Negative Logits
MOESM
-1.75
Respondents
-1.63
aning
-1.58
llll
-1.57
·
-1.54
vain
-1.52
TY
-1.49
others
-1.46
aco
-1.45
aved
-1.45
POSITIVE LOGITS
imization
1.84
caster
1.83
pective
1.75
permits
1.71
casters
1.68
mechanism
1.66
gap
1.60
imum
1.60
identifier
1.59
contender
1.58
Activations Density 0.018%