INDEX
Explanations
paragraphs related to scientific laws and their applications, specifically focusing on fluid dynamics and transport phenomena
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
876
+0.16
0.5%
1385
+0.14
0.5%
50
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
736
+0.16
0.06
1499
+0.14
0.05
51
+0.13
0.02
Negative Logits
Espèce
-0.83
gawas
-0.64
nahilalakip
-0.63
mybatisplus
-0.63
parteci
-0.61
SourceChecksum
-0.60
Bundestag
-0.60
notor
-0.59
Rektor
-0.59
Palestina
-0.58
POSITIVE LOGITS
embodi
1.42
disagre
1.37
increa
1.33
withal
1.31
ftu
1.28
poff
1.26
vns
1.26
ftre
1.25
aen
1.24
wikihow
1.24
Activations Density 0.612%