INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    apag
    -0.08
    IB
    -0.07
    -edge
    -0.07
    [w
    -0.07
    #define
    -0.07
     pato
    -0.07
    nder
    -0.07
    _BINARY
    -0.07
    amboo
    -0.07
     diskut
    -0.07
    POSITIVE LOGITS
     cea
    0.08
     hym
    0.08
     midd
    0.08
     phẩm
    0.07
     AED
    0.07
     Mug
    0.07
     consciência
    0.07
     kath
    0.07
     Fel
    0.07
     Guerra
    0.07
    Act Density 0.001%

    No Known Activations