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

    Neuronpedia

    INDEX
    Explanations

    references to marriage and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ยอด
    -0.64
     blueberries
    -0.64
     bénévol
    -0.64
    orghe
    -0.62
    HEET
    -0.62
    /*
    -0.62
    jména
    -0.61
    heets
    -0.61
     Beale
    -0.60
    degard
    -0.60
    POSITIVE LOGITS
     married
    1.43
     Marriage
    1.36
     marriage
    1.35
     Married
    1.33
    married
    1.27
    Marriage
    1.26
     marry
    1.25
     marriages
    1.22
    Married
    1.20
     matrimon
    1.17
    Act Density 0.135%

    No Known Activations