INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Row
    -0.07
    3
    -0.07
    2
    -0.07
     McCain
    -0.07
     baseline
    -0.07
     guaranteed
    -0.07
     Leah
    -0.07
     rein
    -0.07
     Kevin
    -0.07
    958
    -0.07
    POSITIVE LOGITS
     transport
    0.17
    transport
    0.15
     Transport
    0.14
     transported
    0.14
     transporting
    0.12
     transportation
    0.11
    .transport
    0.11
    Transport
    0.10
     transports
    0.10
     Transportation
    0.10
    Act Density 0.012%

    No Known Activations