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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and public personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     à¨
    -0.69
    cgi
    -0.68
    Mount
    -0.65
    RAL
    -0.64
    CAP
    -0.63
    ãĥķãĤ¡
    -0.63
     Artemis
    -0.63
     FAT
    -0.61
    olulu
    -0.61
     Nicotine
    -0.61
    POSITIVE LOGITS
     aides
    0.93
     himself
    0.90
     supporters
    0.88
    's
    0.85
     campaigned
    0.85
     detractors
    0.82
     tweeted
    0.81
     joked
    0.81
     vetoed
    0.81
     remarked
    0.79
    Act Density 0.235%

    No Known Activations