INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -weight
    -0.09
    editable
    -0.07
    .log
    -0.07
    ensity
    -0.07
    -up
    -0.07
    iliation
    -0.07
    du
    -0.07
    iliar
    -0.07
     Breit
    -0.07
    .s
    -0.07
    POSITIVE LOGITS
     __________________
    0.09
     japan
    0.09
    _soc
    0.09
     FREE
    0.08
     Baseball
    0.08
     baseball
    0.08
     golf
    0.08
    0.08
     Toc
    0.08
     policym
    0.08
    Act Density 0.004%

    No Known Activations