INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.07
     BOOK
    -0.07
    adapt
    -0.07
    -0.07
     Plastic
    -0.07
     Neck
    -0.07
    -0.07
    шт
    -0.07
     neck
    -0.07
    Nick
    -0.06
    POSITIVE LOGITS
     foreground
    0.15
    Foreground
    0.10
    foreground
    0.10
     fg
    0.09
    sofar
    0.07
    0.07
    wg
    0.07
     heraus
    0.07
    .setForeground
    0.07
    ROID
    0.07
    Act Density 0.001%

    No Known Activations