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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advertisements or promotions

    oai_token-act-pair · gpt-3.5-turbo

    references to "advertising."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.77
     sidx
    -0.76
    Ń·
    -0.73
     salv
    -0.69
     backwards
    -0.65
    ãĤ¡
    -0.65
    Ļ½
    -0.63
     Myers
    -0.63
    OIL
    -0.63
     sclerosis
    -0.62
    POSITIVE LOGITS
    venture
    1.29
    ventures
    1.18
    illac
    1.14
    visor
    1.12
    vance
    1.12
    idas
    1.05
    rill
    1.01
    vantage
    1.00
    itionally
    0.96
    ragon
    0.96
    Act Density 0.023%

    No Known Activations