INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -1.13
     भी
    -1.12
     не
    -1.12
     ко
    -1.10
    -1.10
     про
    -1.09
     но
    -1.09
    所有
    -1.09
    ার
    -1.09
     الف
    -1.08
    POSITIVE LOGITS
    <bos>
    13.11
     encomp
    4.74
     fuf
    4.73
     guarante
    4.67
     affor
    4.66
     effe
    4.65
     squa
    4.64
     fta
    4.61
     increa
    4.61
     secon
    4.58
    Act Density 0.781%

    No Known Activations

    This feature has no known activations.