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

    Neuronpedia

    INDEX
    Explanations

    references to achieving fame or recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to fame and its different aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTS
    -0.63
     groceries
    -0.62
    atives
    -0.61
    ajor
    -0.60
     Agg
    -0.59
     halves
    -0.58
    ework
    -0.58
     Genocide
    -0.57
     tense
    -0.56
    lements
    -0.56
    POSITIVE LOGITS
    æ©
    0.85
     fame
    0.83
    stroke
    0.80
     seeker
    0.79
     tremend
    0.79
    rities
    0.75
    stars
    0.75
    frey
    0.75
    ":""},{"
    0.73
     certs
    0.73
    Act Density 0.025%

    No Known Activations