INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .Username
    -0.08
    (phone
    -0.07
    _skin
    -0.07
    (newValue
    -0.07
     Festival
    -0.07
    -cur
    -0.07
    _blog
    -0.07
    _User
    -0.07
    𝐥
    -0.07
    _TRI
    -0.07
    POSITIVE LOGITS
     roots
    0.08
     guit
    0.08
     отлича
    0.07
     WithEvents
    0.07
     mounting
    0.07
    0.07
    指甲
    0.07
     אינם
    0.07
    0.07
     deflect
    0.07
    Act Density 0.002%

    No Known Activations