INDEX
Explanations
foreign language origin/names
New Auto-Interp
Negative Logits
translated
0.63
Transl
0.57
Translation
0.56
translation
0.55
translate
0.55
translates
0.55
翻译
0.53
Translation
0.52
перевод
0.51
translator
0.51
POSITIVE LOGITS
англ
0.47
بالإنجليزية
0.39
来自
0.36
elems
0.36
originally
0.36
оригі
0.36
㵴
0.36
㴌
0.36
terbury
0.35
+}(
0.35
Activations Density 0.018%