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

    Neuronpedia

    INDEX
    Explanations

    references to access, particularly in the context of information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    c
    -0.17
    ationToken
    -0.16
    offee
    -0.16
    lets
    -0.15
    ish
    -0.14
    stanbul
    -0.14
    ishly
    -0.14
    ly
    -0.14
    ternet
    -0.14
    COME
    -0.13
    POSITIVE LOGITS
    ibly
    0.29
    ibilities
    0.20
    orial
    0.18
    yonel
    0.18
    ions
    0.17
    ibility
    0.17
    IBILITY
    0.17
    åĪ°çļĦ
    0.17
    ibilit
    0.17
    ses
    0.16
    Act Density 0.037%

    No Known Activations