INDEX
Explanations
mentions of the term "Ne", which likely refers to a specific entity or concept in the text
New Auto-Interp
Negative Logits
x
-0.15
é¡
-0.15
ler
-0.15
ordable
-0.15
itesse
-0.15
sek
-0.15
esty
-0.14
Fraser
-0.14
lat
-0.14
ree
-0.14
POSITIVE LOGITS
ptune
0.22
Ne
0.19
emiah
0.17
braska
0.17
ighbours
0.16
ighbour
0.16
ibu
0.16
Äįas
0.16
CESS
0.16
urope
0.16
Activations Density 0.015%