INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reluct
    -8.34
     shenan
    -8.27
     impra
    -7.97
     unspeak
    -7.95
     increa
    -7.88
     depic
    -7.85
     disagre
    -7.83
     encomp
    -7.83
     apprehen
    -7.68
     maneu
    -7.50
    POSITIVE LOGITS
    <bos>
    7.99
     Walkover
    3.39
     Himo
    2.96
     Paglinawan
    2.86
     himo
    2.76
     ***!
    2.74
     <",
    2.68
     Shetterly
    2.66
    expandindo
    2.66
     '\\;'
    2.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.