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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing inclusivity or universality

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity and the notion of "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.75
    illac
    -0.69
    ritic
    -0.65
    SHIP
    -0.64
    fman
    -0.64
    lav
    -0.62
    utsche
    -0.60
    edin
    -0.60
     Caption
    -0.60
    IDS
    -0.60
    POSITIVE LOGITS
     kinds
    1.26
    ocating
    1.23
     sorts
    1.23
    igators
    1.04
    iances
    1.03
    usions
    0.95
    igator
    0.95
    iance
    0.94
    owing
    0.93
     facets
    0.92
    Act Density 0.124%

    No Known Activations