INDEX
Explanations
references to elderly individuals and their care
New Auto-Interp
Negative Logits
underage
-0.16
IGIN
-0.14
entine
-0.14
411
-0.13
olie
-0.13
aos
-0.13
orra
-0.13
aben
-0.13
Zak
-0.13
.abort
-0.13
POSITIVE LOGITS
noÅĽci
0.16
usan
0.15
(age
0.15
-aged
0.15
acent
0.15
aged
0.14
furt
0.14
brit
0.14
/pub
0.14
ambre
0.14
Activations Density 0.071%