INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     It
    1.30
    is
    1.22
    it
    1.15
     This
    1.02
     They
    1.01
     That
    0.99
    on
    0.98
    un
    0.98
    are
    0.98
    of
    0.96
    POSITIVE LOGITS
    ем
    1.14
    1.12
     accueill
    0.94
     jeopard
    0.92
    ;
    0.90
    .
    0.88
    ,
    0.86
     noy
    0.85
    ون
    0.82
     hurt
    0.80
    Act Density 0.029%

    No Known Activations