INDEX
Explanations
references to translation and translated works
New Auto-Interp
Negative Logits
bour
-0.15
ĨĴ
-0.15
issa
-0.14
ioni
-0.14
-0.14
rac
-0.14
chang
-0.14
Yoshi
-0.13
elli
-0.13
ance
-0.13
POSITIVE LOGITS
translation
0.73
translated
0.68
translations
0.66
Translation
0.65
translator
0.63
translate
0.62
translation
0.62
translators
0.62
translating
0.59
translated
0.58
Activations Density 0.264%