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

    Neuronpedia

    INDEX
    Explanations

    the word "bon" or variations of it in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "bon" and its variations, which relate to authenticity or legitimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PG
    -0.65
     Spy
    -0.64
     Equity
    -0.63
    enza
    -0.62
     Nicotine
    -0.62
     Dys
    -0.61
     Debt
    -0.60
     Fiction
    -0.60
     Integ
    -0.60
    pta
    -0.60
    POSITIVE LOGITS
     fide
    1.09
    uit
    1.00
    iously
    0.93
    ificial
    0.93
     bon
    0.93
    uitous
    0.90
    uin
    0.90
    anza
    0.88
    eless
    0.88
    bon
    0.88
    Act Density 0.021%

    No Known Activations