INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    foundland
    -0.84
     pleaſure
    -0.84
     ſy
    -0.79
    ual
    -0.79
     Anſ
    -0.79
     Monfieur
    -0.79
     myſelf
    -0.76
     Theſe
    -0.75
     étoient
    -0.73
     avoient
    -0.73
    POSITIVE LOGITS
    0.56
    <eos>
    0.55
    ↵↵
    0.50
    js
    0.49
     kaarangay
    0.48
    0.48
     State
    0.47
    XmlAccessType
    0.47
     InputDecoration
    0.47
    ,
    0.47
    Act Density 0.257%

    No Known Activations