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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or possession

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.76
    imar
    -0.70
    ilde
    -0.67
    ork
    -0.66
    airs
    -0.65
    rices
    -0.65
    aptic
    -0.62
     Hurricanes
    -0.61
    annis
    -0.61
    aul
    -0.60
    POSITIVE LOGITS
     belong
    0.81
     belonged
    0.81
    ĪĴ
    0.79
    itialized
    0.79
     belongs
    0.74
    holder
    0.72
    itors
    0.70
     belonging
    0.70
    REDACTED
    0.70
    BuyableInstoreAndOnline
    0.69
    Act Density 0.014%

    No Known Activations