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
    sog
    -0.63
    degard
    -0.63
    hagen
    -0.62
     Coli
    -0.60
    HEET
    -0.60
     Beale
    -0.58
     Aether
    -0.58
     blueberries
    -0.58
    orghe
    -0.58
     tens
    -0.57
    POSITIVE LOGITS
     married
    2.10
     Married
    1.93
     marriage
    1.85
    married
    1.85
     marry
    1.84
     Marriage
    1.84
    Marriage
    1.73
    Married
    1.73
     marriages
    1.71
     marries
    1.63
    Act Density 0.098%

    No Known Activations