INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -founded
    -0.08
     Vet
    -0.08
    Deadline
    -0.08
     Bold
    -0.08
     Dennis
    -0.07
    -0.07
    Friendly
    -0.07
     Breeze
    -0.07
     Hef
    -0.07
    _blank
    -0.07
    POSITIVE LOGITS
     rotational
    0.09
     rotations
    0.08
     trick
    0.08
     overpower
    0.08
    -square
    0.07
    .Picture
    0.07
    .picture
    0.07
     picture
    0.07
    .rot
    0.07
    Видео
    0.07
    Act Density 0.013%

    No Known Activations