INDEX
    Explanations

    forms of the word "just."

    New Auto-Interp
    Negative Logits
    Äįi
    -0.17
    .metro
    -0.14
    elight
    -0.14
    dden
    -0.13
    ist
    -0.13
    ate
    -0.13
    cg
    -0.13
    بس
    -0.13
    inton
    -0.13
     Mein
    -0.13
    POSITIVE LOGITS
    ecause
    0.15
    ATA
    0.15
    ³
    0.14
    ÑĢеÑħ
    0.14
    junction
    0.14
    /gtest
    0.14
    ommen
    0.14
    лÑıÑĤÑĮ
    0.14
     because
    0.14
     Aren
    0.14
    Act Density 0.115%

    No Known Activations