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

    Neuronpedia

    INDEX
    Explanations

    instances where credit is being given to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to giving credit or acknowledgment to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lans
    -0.83
    dq
    -0.67
     Osw
    -0.65
     Somers
    -0.65
    ften
    -0.63
     intest
    -0.63
     Weird
    -0.62
    improve
    -0.62
    vae
    -0.61
     Dresden
    -0.61
    POSITIVE LOGITS
    card
    0.82
    worthiness
    0.82
     card
    0.80
    olor
    0.80
     CARD
    0.79
    Credit
    0.79
     credit
    0.79
    enza
    0.78
    itism
    0.77
    cards
    0.74
    Act Density 0.018%

    No Known Activations