INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Firstly
    -1.57
     firstly
    -1.48
     myſelf
    -1.41
     Jefus
    -1.40
     purpoſe
    -1.38
     Majefty
    -1.38
     itſelf
    -1.34
     ſtate
    -1.34
     Monfieur
    -1.30
    ſelf
    -1.23
    POSITIVE LOGITS
    ,
    1.23
     (
    0.82
     A
    0.75
     in
    0.74
     for
    0.74
    0.72
     and
    0.71
    /
    0.71
     "
    0.71
    <eos>
    0.70
    Act Density 2.147%

    No Known Activations