INDEX
Explanations
details about hotel amenities and meeting spaces offered
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.26
0.9%
1013
+0.10
0.4%
1870
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1013
+0.26
0.05
469
+0.10
0.04
1960
+0.10
0.04
Negative Logits
<bos>
-2.56
ⓧ
-0.76
InjectMocks
-0.66
introduce
-0.63
Cyfarwyddwr
-0.62
CreateModel
-0.62
prioritize
-0.61
/**
-0.61
뤄
-0.61
hope
-0.60
POSITIVE LOGITS
lele
1.48
bandung
1.37
swarovski
1.33
impra
1.33
mef
1.30
ecru
1.30
hcm
1.29
keramik
1.29
valencia
1.28
embodi
1.28
Activations Density 0.323%