INDEX
Explanations
mentions of medical conditions related to babies
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
90
+0.12
0.4%
1602
+0.11
0.4%
11
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1602
+0.12
0.02
908
+0.11
0.02
11
+0.10
0.02
Negative Logits
Constipation
-0.44
nawr
-0.43
дыду
-0.41
glitter
-0.41
łgorzata
-0.41
altrimenti
-0.41
endometriosis
-0.40
risulta
-0.40
occorre
-0.40
palpit
-0.40
POSITIVE LOGITS
baby
1.32
Baby
1.22
Baby
1.21
baby
1.20
babies
1.13
BABY
1.12
Babies
1.00
BABY
0.99
babies
0.90
Babies
0.88
Activations Density 0.078%