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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organization and decluttering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.15
    hti
    -0.15
    illard
    -0.15
    çĭ¬ç«ĭ
    -0.15
    Independent
    -0.15
    wat
    -0.14
    Äįet
    -0.14
    ugas
    -0.14
    رÙĪس
    -0.14
    кÑĥÑģ
    -0.14
    POSITIVE LOGITS
    æ°¸
    0.15
    ива
    0.14
    owe
    0.14
    /loose
    0.14
     adults
    0.14
    erals
    0.14
     pill
    0.13
     fats
    0.13
     Soda
    0.13
    463
    0.13
    Act Density 0.064%

    No Known Activations