INDEX
    Explanations

    names and terms related to locations, institutions, or specific people

    New Auto-Interp
    Negative Logits
    ameda
    -0.15
    aryana
    -0.15
    رÙĪÛĮ
    -0.14
    urette
    -0.14
    \Bridge
    -0.14
    몰
    -0.14
    ÑĢÑĸв
    -0.14
    ampled
    -0.14
    INES
    -0.14
     Ekon
    -0.13
    POSITIVE LOGITS
    older
    0.16
    osate
    0.15
    rough
    0.14
    á»ı
    0.14
    lyph
    0.14
    gary
    0.14
    ubu
    0.14
    ç¶ļ
    0.14
     dál
    0.13
    yet
    0.13
    Act Density 0.184%

    No Known Activations