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

    Neuronpedia

    INDEX
    Explanations

    actions related to legal or formal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.15
    eller
    -0.14
    hood
    -0.14
    æĿIJ
    -0.14
    ville
    -0.14
    βο
    -0.13
    esters
    -0.13
    iest
    -0.13
    aji
    -0.13
     Weston
    -0.13
    POSITIVE LOGITS
    TRL
    0.17
    PCS
    0.15
     ohled
    0.15
     Äijây
    0.14
    Which
    0.14
     which
    0.14
    inclu
    0.14
    uxtap
    0.14
    which
    0.14
     навк
    0.14
    Act Density 0.321%

    No Known Activations