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

    Neuronpedia

    INDEX
    Explanations

    words related to processes, mechanisms, and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luet
    -0.15
    ANGLES
    -0.14
    ниÑģÑĤ
    -0.14
    chia
    -0.14
    BOOT
    -0.14
    ovny
    -0.14
     Roose
    -0.14
    STYPE
    -0.14
    $MESS
    -0.14
    ÑĤоÑĦ
    -0.14
    POSITIVE LOGITS
    _fa
    0.14
    pread
    0.14
    agues
    0.14
    ourcem
    0.13
    gars
    0.13
     Plus
    0.13
     Hers
    0.13
    odu
    0.13
    iveness
    0.13
    ged
    0.13
    Act Density 0.103%

    No Known Activations