INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ara
    0.86
    ak
    0.78
    á
    0.75
    S
    0.65
    ar
    0.63
    AN
    0.61
    ábor
    0.61
    este
    0.60
    E
    0.60
    google
    0.58
    POSITIVE LOGITS
     the
    0.73
     an
    0.71
     these
    0.69
     both
    0.65
     firearms
    0.65
     sales
    0.64
     scenarios
    0.62
     this
    0.60
     say
    0.60
     competing
    0.60
    Act Density 0.052%

    No Known Activations