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

    Neuronpedia

    INDEX
    Explanations

    content related to rules and conditions in policy statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eing
    -0.14
     æĿ¡
    -0.14
    óng
    -0.14
    eting
    -0.14
    osi
    -0.14
    vana
    -0.14
    cing
    -0.13
    _IB
    -0.13
    IES
    -0.13
    _IMPL
    -0.13
    POSITIVE LOGITS
    terra
    0.14
    ORITY
    0.14
    ché
    0.14
    عÙĦÛĮ
    0.14
    /calendar
    0.14
    addon
    0.14
    /copyleft
    0.14
    ollar
    0.14
    ξι
    0.14
    reck
    0.13
    Act Density 0.655%

    No Known Activations