INDEX
Explanations
references to leisure activities and personal interests
New Auto-Interp
Negative Logits
иÑģÑģ
-0.16
sÃŃ
-0.14
MUT
-0.14
گرد
-0.14
gratis
-0.14
aine
-0.13
aire
-0.13
Categoria
-0.13
anter
-0.13
é
-0.13
POSITIVE LOGITS
itler
0.15
WebRequest
0.15
emachine
0.14
bÅĻez
0.14
ipples
0.14
.Compiler
0.14
onio
0.13
ãģŁãĤĬ
0.13
serter
0.13
targ
0.13
Activations Density 0.030%