INDEX
    Explanations

    hyphens/dashes

    New Auto-Interp
    Negative Logits
     Rather
    -0.07
    .ext
    -0.07
    .PictureBoxSizeMode
    -0.07
     Plaint
    -0.07
     royalty
    -0.07
    ']↵↵↵
    -0.07
     *↵↵↵
    -0.07
     המחיר
    -0.07
    _HAS
    -0.06
     accommodations
    -0.06
    POSITIVE LOGITS
     passer
    0.07
     Eating
    0.07
    ComputedStyle
    0.07
    Piece
    0.07
     repell
    0.07
    arming
    0.06
     rais
    0.06
     rend
    0.06
     bitten
    0.06
    utt
    0.06
    Act Density 0.004%

    No Known Activations