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

    Neuronpedia

    INDEX
    Explanations

    references to buttons in a user interface or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mons
    -0.19
    thora
    -0.17
    ilik
    -0.15
    abeth
    -0.15
    /sdk
    -0.15
    izo
    -0.14
     tabBar
    -0.14
    hev
    -0.14
     Seymour
    -0.14
    æ³³
    -0.14
    POSITIVE LOGITS
     Fel
    0.17
    669
    0.15
    atri
    0.15
    تÙģ
    0.14
    oins
    0.14
    atar
    0.14
     Baba
    0.14
    à¸İ
    0.14
    _GLOBAL
    0.14
    oren
    0.14
    Act Density 0.010%

    No Known Activations