INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    .scalar
    -0.06
    BoxLayout
    -0.06
     Mature
    -0.06
    řik
    -0.06
    Knife
    -0.06
    daş
    -0.06
    _leaf
    -0.06
    unto
    -0.06
    âh
    -0.06
    ژه
    -0.06
    POSITIVE LOGITS
    -loving
    0.06
    -born
    0.06
    VML
    0.06
     Fuse
    0.06
     apprec
    0.06
     Interpret
    0.06
     mixing
    0.06
    ^^^^
    0.06
    ені
    0.06
    0.06
    Act Density 0.017%

    No Known Activations