INDEX
Explanations
numbers and anatomical words related to the eye
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1806
+0.15
0.5%
1964
+0.14
0.5%
597
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1964
+0.15
0.03
1806
+0.14
0.03
990
+0.13
0.03
Negative Logits
lez
-0.51
Literat
-0.51
Geoffrey
-0.45
Suom
-0.44
uillez
-0.44
stamo
-0.43
Πηγές
-0.43
Parcelize
-0.42
kura
-0.42
contribue
-0.42
POSITIVE LOGITS
eye
1.27
eye
1.24
Eye
1.23
Eye
1.22
Eyes
1.21
EYE
1.19
eyes
1.19
EYES
1.17
eyes
1.17
Eyes
1.12
Activations Density 0.085%