INDEX
Explanations
text related to political events and economic systems
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
184
+0.12
0.3%
1473
+0.09
0.3%
442
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1473
+0.12
0.02
191
+0.09
0.02
1799
+0.09
0.01
Negative Logits
reluct
-1.75
snoopy
-1.70
shenan
-1.69
milf
-1.58
volunte
-1.55
emphat
-1.55
purcha
-1.55
disagre
-1.54
depic
-1.52
affor
-1.49
POSITIVE LOGITS
fjspx
0.72
استنادى
0.71
AssemblyCulture
0.71
aarrggbb
0.71
GenerationType
0.68
getItemCount
0.67
jsPsych
0.67
typelib
0.66
relenting
0.66
AndEndTag
0.65
Activations Density 0.095%