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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unday
    -0.15
    rollo
    -0.15
    geist
    -0.15
    át
    -0.14
    yes
    -0.14
    INA
    -0.14
    idel
    -0.13
    shadow
    -0.13
     undert
    -0.13
    Ñħов
    -0.13
    POSITIVE LOGITS
    ogany
    0.17
    ëł
    0.16
     Sheridan
    0.15
    arget
    0.14
    ISON
    0.14
    (exports
    0.14
    Schedulers
    0.14
    ırak
    0.14
    skb
    0.14
    É
    0.14
    Act Density 0.023%

    No Known Activations