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

    Neuronpedia

    INDEX
    Explanations

    references to advertisements

    oai_token-act-pair · gpt-3.5-turbo

    references to advertisements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.79
    lihood
    -0.72
     Cyprus
    -0.70
    IFE
    -0.69
    ^^^^
    -0.68
     IPCC
    -0.68
    theless
    -0.68
     Ryder
    -0.67
     Patriarch
    -0.66
    20439
    -0.66
    POSITIVE LOGITS
    vertising
    1.13
     ads
    1.12
     advertising
    0.98
    vertisements
    0.94
     billboards
    0.90
    idas
    0.90
     advertisements
    0.90
    elaide
    0.89
    vertis
    0.89
    vertisement
    0.87
    Act Density 0.015%

    No Known Activations