INDEX
    Explanations

    mentions of a specific name, "Braz" or variations thereof, possibly related to a person or a topic of interest

    mentions of specific names, particularly those related to political figures

    New Auto-Interp
    Negative Logits
     Apollo
    -0.73
     Manson
    -0.71
     Pearce
    -0.68
    vironment
    -0.65
     parachute
    -0.63
    anguage
    -0.63
     skate
    -0.62
     modification
    -0.61
     Mercury
    -0.61
     cave
    -0.61
    POSITIVE LOGITS
    let
    0.93
    ular
    0.87
    ility
    0.85
     Bras
    0.85
    lets
    0.84
    ilia
    0.83
    aign
    0.82
    ão
    0.82
    inas
    0.81
    iod
    0.81
    Act Density 0.021%

    No Known Activations