INDEX
Explanations
names of places/people related to the field of education
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1937
+0.19
1.1%
313
+0.17
0.9%
481
+0.16
0.9%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1937
+0.19
0.04
1097
+0.17
0.04
1741
+0.16
0.00
Negative Logits
<bos>
-1.30
zo
-0.62
ibatis
-0.61
Hãy
-0.59
Đi
-0.57
iddharth
-0.57
ממ
-0.56
jspx
-0.56
Zo
-0.56
ക
-0.55
POSITIVE LOGITS
Lawrence
1.50
LAWRENCE
1.44
Lawrence
1.43
maneu
1.27
wien
1.27
depic
1.26
doraemon
1.26
!...
1.26
pixar
1.26
ftu
1.26
Activations Density 0.430%