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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating diverse options or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.19
    isters
    -0.19
    efeller
    -0.17
    ertz
    -0.16
    ent
    -0.15
    /player
    -0.15
    ses
    -0.14
    åIJĦç§į
    -0.14
    upt
    -0.14
    ipt
    -0.14
    POSITIVE LOGITS
    ulence
    0.19
    /div
    0.18
    ERTICAL
    0.17
    batim
    0.17
    ulent
    0.17
    kker
    0.17
    /ext
    0.15
    degrees
    0.15
    iances
    0.15
    asmus
    0.15
    Act Density 0.049%

    No Known Activations