INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Frame
    -0.07
    _Impl
    -0.07
     framed
    -0.07
    ALLERY
    -0.07
     اخلاق
    -0.07
     Leigh
    -0.07
     alpha
    -0.07
    Edit
    -0.06
    економ
    -0.06
    Crit
    -0.06
    POSITIVE LOGITS
     Song
    0.13
     song
    0.13
    Song
    0.12
     songs
    0.09
    song
    0.09
    -song
    0.08
    0.08
    (song
    0.08
     Songs
    0.08
     Tong
    0.07
    Act Density 0.014%

    No Known Activations