INDEX
    Explanations

    intended, hoped, or expected

    New Auto-Interp
    Negative Logits
     think
    0.72
     dần
    0.69
    think
    0.69
    อด
    0.68
    ੱਚ
    0.67
     pendek
    0.65
     বলব
    0.64
    に残
    0.64
     ایل
    0.62
     Played
    0.62
    POSITIVE LOGITS
     normally
    1.46
     customarily
    1.32
    Normally
    1.28
     intended
    1.28
     requested
    1.27
     usually
    1.27
     hoped
    1.26
     Normally
    1.24
     ordinarily
    1.20
     expected
    1.19
    Act Density 0.198%

    No Known Activations