INDEX
Explanations
the word "you" in various contexts and forms
New Auto-Interp
Negative Logits
prenom
-0.15
ichten
-0.15
icht
-0.15
ÑĥÑģÑĤа
-0.14
atsby
-0.14
glich
-0.14
haar
-0.14
UBLIC
-0.14
dana
-0.14
±
-0.14
POSITIVE LOGITS
eter
0.17
iro
0.16
_rc
0.14
Caption
0.14
stro
0.14
Responder
0.14
869
0.14
enge
0.14
PI
0.14
ced
0.14
Activations Density 0.012%