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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating that something should be interpreted in a particular way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "viewed" and its related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ften
    -0.72
    backer
    -0.70
    nown
    -0.63
    ammy
    -0.61
    weather
    -0.61
    vous
    -0.60
    breaker
    -0.60
     Laurent
    -0.59
    yan
    -0.59
    cover
    -0.59
    POSITIVE LOGITS
    ById
    0.99
    phas
    0.83
    æѦ
    0.79
     favorably
    0.79
    ĸ
    0.77
    ª
    0.76
    æĦ
    0.75
    ASED
    0.74
    isions
    0.74
    Ĺ
    0.73
    Act Density 0.044%

    No Known Activations