INDEX
    Explanations

    mentions of the name "Bush" at a particularly high activation level

    references to former President Bush and his administration's actions

    New Auto-Interp
    Negative Logits
    semble
    -0.72
     Qiao
    -0.67
     Cth
    -0.65
    Else
    -0.64
     Norn
    -0.62
     Harmony
    -0.62
    ymph
    -0.62
     clipboard
    -0.60
    feature
    -0.60
     Pixie
    -0.60
    POSITIVE LOGITS
    nell
    1.21
    ido
    1.05
    master
    0.93
    lett
    0.92
    minster
    0.80
    Bush
    0.80
     Hussein
    0.78
    men
    0.78
    enegger
    0.76
    bour
    0.76
    Act Density 0.014%

    No Known Activations