INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     shepherd
    -0.07
    _ends
    -0.07
     Focus
    -0.07
     Beatles
    -0.07
     Goal
    -0.07
    -basket
    -0.06
    жу
    -0.06
     захисту
    -0.06
     accommodate
    -0.06
    esture
    -0.06
    POSITIVE LOGITS
     syrup
    0.12
     sip
    0.07
     Synd
    0.07
    ,要
    0.07
     VT
    0.07
    sim
    0.07
     sympathy
    0.06
    수로
    0.06
    OP
    0.06
     Sy
    0.06
    Act Density 0.001%

    No Known Activations