Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    news media sources and related entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news organizations or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.73
    figure
    -0.70
    cffffcc
    -0.67
    }}}
    -0.64
    ãĥ¡
    -0.61
    Rated
    -0.58
    emort
    -0.56
    chieve
    -0.55
    Lenin
    -0.55
    .}
    -0.54
    POSITIVE LOGITS
     that
    1.04
     he
    0.87
     they
    0.86
    that
    0.82
     she
    0.79
     there
    0.75
     it
    0.67
    è¦ļéĨĴ
    0.65
     beforehand
    0.64
     "[
    0.64
    Act Density 0.089%

    No Known Activations