INDEX
    Explanations

    expressions of desire or longing

    New Auto-Interp
    Negative Logits
     Majefty
    -0.69
     myſelf
    -0.65
     ſeveral
    -0.61
     itſelf
    -0.58
     alſo
    -0.58
     themſelves
    -0.57
     Reſ
    -0.56
    DataAnnotations
    -0.56
    TemporalType
    -0.56
     ſever
    -0.55
    POSITIVE LOGITS
     envy
    0.71
    Wish
    0.60
     Wish
    0.59
     wish
    0.56
     regretted
    0.55
    untung
    0.52
     WISH
    0.52
     Envy
    0.52
    羡慕
    0.52
     کاش
    0.51
    Act Density 0.158%

    No Known Activations