INDEX
Explanations
objects and items related to living spaces and household fixtures
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.26
1.0%
1870
+0.13
0.5%
1385
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1385
+0.26
0.12
1013
+0.13
0.09
1870
+0.12
0.06
Negative Logits
<bos>
-2.36
solidar
-0.81
/***
-0.81
///**
-0.78
MessageOf
-0.74
HasAnnotation
-0.74
TextEditing
-0.71
drap
-0.69
spontan
-0.67
//---
-0.66
POSITIVE LOGITS
embodi
1.19
Hahah
1.02
Ename
1.01
impractica
0.99
Noice
0.98
Minang
0.95
Fitment
0.95
Ohhhh
0.93
liberality
0.93
Ehh
0.93
Activations Density 0.727%