INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     obtain
    -2.03
     obtains
    -1.98
     obtaining
    -1.88
     obtained
    -1.86
     Obtain
    -1.84
    obtain
    -1.82
     Obtaining
    -1.77
     gain
    -1.73
     Obtained
    -1.73
    obtained
    -1.72
    POSITIVE LOGITS
     a
    0.61
     the
    0.54
    ########.
    0.52
    ment
    0.52
     an
    0.51
     some
    0.51
     and
    0.49
     those
    0.46
     so
    0.46
    ctools
    0.46
    Act Density 0.228%

    No Known Activations