INDEX
    Explanations

    colloquial expressions and interjections that convey a casual tone or hesitation

    New Auto-Interp
    Negative Logits
    celik
    -0.17
    igy
    -0.15
    udos
    -0.15
    wik
    -0.14
    اط
    -0.14
    wg
    -0.14
    utting
    -0.14
    udit
    -0.14
    eway
    -0.14
     Redistributions
    -0.14
    POSITIVE LOGITS
     well
    0.39
     er
    0.33
    well
    0.29
     um
    0.29
     wait
    0.26
     shall
    0.25
     err
    0.24
     uh
    0.23
     Well
    0.22
     ah
    0.21
    Act Density 0.094%

    No Known Activations