INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -times
    -0.07
     Access
    -0.07
    -posts
    -0.07
     Decode
    -0.07
     Disable
    -0.06
    spawn
    -0.06
     Exchange
    -0.06
    _output
    -0.06
    _rel
    -0.06
    Entry
    -0.06
    POSITIVE LOGITS
     Solo
    0.07
     solo
    0.07
    thumb
    0.06
    Solo
    0.06
    183
    0.06
    ой
    0.06
    ุ้
    0.06
     CB
    0.06
    >()->
    0.06
    **************
    0.06
    Act Density 0.002%

    No Known Activations