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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and family interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    τως
    -0.73
    లాలు
    -0.66
     cherchés
    -0.62
    kusen
    -0.62
    发表于
    -0.59
     pymongo
    -0.58
     lenker
    -0.56
    komme
    -0.55
    OLOGÍA
    -0.55
    ranean
    -0.54
    POSITIVE LOGITS
     gelieb
    0.60
     loved
    0.60
     happiest
    0.59
     unforgettable
    0.55
     always
    0.55
    createComponent
    0.55
     laughter
    0.55
     proudest
    0.55
    buttonBar
    0.53
     lovingly
    0.53
    Act Density 0.059%

    No Known Activations