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

    Neuronpedia

    INDEX
    Explanations

    symbols or formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efined
    -0.18
    ial
    -0.17
    htt
    -0.14
    LOBAL
    -0.14
    idebar
    -0.14
    ities
    -0.14
    antly
    -0.14
    ddb
    -0.14
    stab
    -0.14
    uty
    -0.14
    POSITIVE LOGITS
    ka
    0.17
    ÛĮز
    0.16
    kan
    0.16
    enk
    0.15
    _atts
    0.14
    zo
    0.14
    enek
    0.14
    enberg
    0.14
    isque
    0.13
    jd
    0.13
    Act Density 0.059%

    No Known Activations