INDEX
Explanations
numeric values related to financial or statistical data
New Auto-Interp
Negative Logits
ship
-0.20
lie
-0.18
table
-0.18
views
-0.17
athers
-0.17
liness
-0.17
ple
-0.16
ning
-0.16
pill
-0.16
ships
-0.15
POSITIVE LOGITS
ughter
0.19
0.18
³³³³³
0.17
arend
0.16
ydı
0.16
eker
0.16
empre
0.15
ity
0.15
urch
0.14
stro
0.14
Activations Density 0.141%