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

    Neuronpedia

    INDEX
    Explanations

    mentions of loved ones or relationships with loved ones

    oai_token-act-pair · gpt-3.5-turbo

    references to loved ones and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.87
    interstitial
    -0.79
    illin
    -0.68
    arat
    -0.68
    authorized
    -0.66
    setup
    -0.64
    taboola
    -0.64
    é¾
    -0.62
    Loading
    -0.61
    arta
    -0.61
    POSITIVE LOGITS
    lihood
    0.94
     uncond
    0.86
    joy
    0.79
    nesday
    0.77
     dearly
    0.72
     Pwr
    0.71
     Serve
    0.70
    itely
    0.68
    rily
    0.67
    tsky
    0.66
    Act Density 0.049%

    No Known Activations