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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Zuma" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Zuma."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neath
    -0.71
    tons
    -0.69
    icles
    -0.69
    ician
    -0.68
     Canadians
    -0.68
    Ö¼
    -0.66
     Kear
    -0.65
    igree
    -0.63
    working
    -0.62
    sheet
    -0.62
    POSITIVE LOGITS
    ppa
    0.99
    uma
    0.97
    BLE
    0.88
    ascus
    0.84
    ULT
    0.81
    UGH
    0.80
    qua
    0.79
    isoft
    0.76
    urs
    0.76
    ffe
    0.73
    Act Density 0.013%

    No Known Activations