INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     slip
    -0.08
     fueled
    -0.08
     posse
    -0.08
     Gerr
    -0.08
    ZG
    -0.07
     BON
    -0.07
    >Z
    -0.07
     Vinc
    -0.07
    bon
    -0.07
     frontière
    -0.07
    POSITIVE LOGITS
     Eisen
    0.08
    Angle
    0.08
     tower
    0.07
     halte
    0.07
    summ
    0.07
    0.07
     closely
    0.07
    0.07
    lined
    0.07
    -(
    0.07
    Act Density 0.001%

    No Known Activations