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

    Neuronpedia

    INDEX
    Explanations

    that something can no longer be done or relied upon

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating impossibility or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.73
    DragonMagazine
    -0.64
    ONES
    -0.64
    soDeliveryDate
    -0.60
    Kings
    -0.59
     Kush
    -0.59
    Land
    -0.56
    HOME
    -0.56
     guiActiveUnfocused
    -0.55
    oresc
    -0.55
    POSITIVE LOGITS
    rouse
    1.19
    venge
    1.18
    rely
    0.88
    etheless
    0.87
    lessly
    0.85
    activate
    0.82
    arily
    0.80
    ize
    0.79
    ean
    0.79
    ceive
    0.77
    Act Density 0.305%

    No Known Activations