INDEX
Explanations
statements and quotes attributed to individuals
New Auto-Interp
Negative Logits
ãĥĥãĥĪ
-0.18
ãĤī
-0.16
hy
-0.15
ies
-0.15
go
-0.14
last
-0.14
rawing
-0.13
acades
-0.13
Ãłng
-0.13
anik
-0.13
POSITIVE LOGITS
warts
0.19
ngle
0.17
नल
0.15
еÑĩ
0.15
lage
0.15
now
0.14
range
0.14
auge
0.14
arded
0.14
datatable
0.14
Activations Density 0.083%