INDEX
Explanations
elements related to home decor and design trends
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
346
+0.12
0.7%
244
+0.12
0.7%
33
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
203
+0.12
0.36
23
+0.12
0.31
494
+0.11
0.25
Negative Logits
lect
-1.62
algia
-1.41
caf
-1.36
hab
-1.35
wered
-1.33
ogly
-1.31
og
-1.31
ensive
-1.29
orted
-1.27
-1.25
POSITIVE LOGITS
¡
3.98
¯
3.64
Ń
3.49
¢
3.38
Ĥ¬
3.34
Ĥ
3.30
¦
3.17
«
3.17
Ļ
3.16
§
3.13
Activations Density 3.055%