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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions and timing related to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ration
    -0.14
    bourg
    -0.14
    orning
    -0.14
    kening
    -0.14
    .mozilla
    -0.13
    ä¸Ī
    -0.13
    еÑĢж
    -0.13
    alist
    -0.13
    sik
    -0.13
     ÏĢÏģÏī
    -0.13
    POSITIVE LOGITS
    ording
    0.17
    vat
    0.16
    evin
    0.16
    è¦ĭ
    0.14
    á»Ŀi
    0.14
    unga
    0.14
    abi
    0.14
    eso
    0.14
    inant
    0.14
    عاÙĨ
    0.14
    Act Density 0.232%

    No Known Activations