INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.79
     propOrder
    -0.79
     ویکی‌پدی
    -0.78
     itſelf
    -0.77
    mybatisplus
    -0.75
     AspNetCore
    -0.74
     pleaſure
    -0.73
     Forumite
    -0.73
     myſelf
    -0.73
     poffe
    -0.72
    POSITIVE LOGITS
    ting
    0.65
    mu
    0.52
    bing
    0.52
    ton
    0.51
    ary
    0.50
    nav
    0.50
    ry
    0.49
    ={<
    0.45
    jwa
    0.44
     mathvariant
    0.44
    Act Density 0.085%

    No Known Activations