INDEX
    Explanations

    mentions of Ethiopia and related terms

    New Auto-Interp
    Negative Logits
     Mev
    -0.15
    avis
    -0.15
    .zh
    -0.15
     trú
    -0.15
     edin
    -0.15
    erif
    -0.14
    ingles
    -0.14
    voke
    -0.14
    ̧
    -0.14
    ilden
    -0.14
    POSITIVE LOGITS
    /name
    0.15
    âķij
    0.15
    uteur
    0.15
    å±¥
    0.15
    CS
    0.14
    è±Ĩ
    0.14
    ophe
    0.14
    ence
    0.14
     Belt
    0.14
    reich
    0.14
    Act Density 0.004%

    No Known Activations