INDEX
Explanations
phrases related to exposure to toxins, specifically lead exposure
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.11
0.3%
630
+0.10
0.3%
1978
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
163
+0.11
0.02
630
+0.10
0.02
193
+0.09
0.02
Negative Logits
GEBURTSDATUM
-0.60
Geplaatst
-0.55
intios
-0.51
sceptre
-0.50
dacht
-0.50
>=",
-0.49
ProtoMessage
-0.49
satchel
-0.49
Personendaten
-0.49
ufc
-0.48
POSITIVE LOGITS
blz
0.57
argint
0.56
Certo
0.55
vasi
0.54
marte
0.53
Į
0.53
Pois
0.52
Infatti
0.52
Doğ
0.52
Ciò
0.51
Activations Density 0.022%