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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ackers
    -0.17
    ÑĥÑģа
    -0.16
    .unknown
    -0.15
    ardo
    -0.15
    æ©
    -0.14
    dings
    -0.13
    isas
    -0.13
    coming
    -0.13
    اÙĨÙĩ
    -0.13
    sharing
    -0.13
    POSITIVE LOGITS
    ively
    0.18
    ãĥ¼ãĤ¿ãĥ¼
    0.15
     Aires
    0.14
    imen
    0.14
    Ļ¨
    0.14
    entially
    0.14
    oo
    0.14
    /assert
    0.13
    IVE
    0.13
    empre
    0.13
    Act Density 0.034%

    No Known Activations