INDEX
    Explanations

    locations and timestamps in the text

    New Auto-Interp
    Negative Logits
    rants
    -0.76
    bum
    -0.73
    istrate
    -0.71
    NetMessage
    -0.70
    idepress
    -0.68
    bernatorial
    -0.68
     showc
    -0.67
    ipolar
    -0.66
    lishes
    -0.66
    channelAvailability
    -0.66
    POSITIVE LOGITS
    cule
    0.71
     USA
    0.68
     aust
    0.68
     sweats
    0.68
     Slovenia
    0.67
     scratch
    0.65
     collaboration
    0.63
     Germany
    0.63
     China
    0.63
     sweat
    0.60
    Act Density 0.572%

    No Known Activations