INDEX
Explanations
first-person pronouns and expressions of personal desire or intention
New Auto-Interp
Negative Logits
kaynağından
-0.71
lemmer
-0.57
bagno
-0.56
rophe
-0.54
temming
-0.51
variedad
-0.51
везе
-0.50
chiha
-0.49
الدراسه
-0.49
ویکیپدی
-0.48
POSITIVE LOGITS
mine
0.73
myſelf
0.72
DotNetBar
0.68
MyBatis
0.68
minha
0.66
comigo
0.65
mía
0.63
Mine
0.62
my
0.59
мои
0.59
Activations Density 0.212%