INDEX
Explanations
terms related to foster care
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.15
0.9%
889
+0.15
0.8%
241
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1895
+0.15
0.01
889
+0.15
0.02
241
+0.14
0.01
Negative Logits
<bos>
-2.18
StoreMessageInfo
-0.65
CodeDom
-0.65
RotationOrder
-0.64
cline
-0.64
Argumento
-0.63
RTDA
-0.63
↘
-0.62
Ос
-0.61
setClass
-0.61
POSITIVE LOGITS
stockholm
1.48
FOSTER
1.45
increa
1.40
FFFF
1.39
embodi
1.38
maneu
1.37
thut
1.36
fta
1.36
greate
1.34
?...
1.34
Activations Density 0.066%