INDEX
Explanations
references to different types of bottles and containers
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
889
+0.17
0.7%
1926
+0.16
0.6%
1573
+0.14
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1926
+0.17
0.02
1573
+0.16
0.02
889
+0.14
0.02
Negative Logits
Himmels
-0.62
vanni
-0.58
calvin
-0.58
ceas
-0.57
triump
-0.56
كومونز
-0.56
dante
-0.55
Leip
-0.55
fap
-0.55
ConstraintMaker
-0.55
POSITIVE LOGITS
bottle
1.47
bottles
1.39
Bottle
1.30
bottle
1.28
Bottle
1.25
Bott
1.20
Bott
1.19
Bottles
1.16
BOTT
1.12
bottled
1.08
Activations Density 0.088%