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

    Neuronpedia

    INDEX
    Explanations

    references to actors and their roles in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оло
    -0.14
    splice
    -0.13
    sandbox
    -0.13
    ož
    -0.13
    .UInt
    -0.12
    bidden
    -0.12
     Äįin
    -0.12
    illac
    -0.12
    ãģĿãģĹãģ¦
    -0.12
    ollo
    -0.12
    POSITIVE LOGITS
    kaç
    0.15
     dit
    0.14
    ecycle
    0.13
     Bryan
    0.13
    elopment
    0.13
    uppe
    0.13
     Morrow
    0.12
     peoples
    0.12
    #
    0.12
    izin
    0.12
    Act Density 0.079%

    No Known Activations