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

    Neuronpedia

    INDEX
    Explanations

    the start of sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.42
    aur
    -0.32
    HomeAsUpEnabled
    -0.32
    ary
    -0.32
     Ca
    -0.31
    o
    -0.31
    s
    -0.31
    Ausbildung
    -0.29
    ↵
    -0.29
    ob
    -0.29
    POSITIVE LOGITS
     houſe
    0.69
     faſt
    0.67
     occaf
    0.67
     Houſe
    0.66
     Majefty
    0.65
    تفصیلات
    0.65
     فريبيس
    0.64
     Paglinawan
    0.61
     fubject
    0.61
    ロウィン
    0.59
    Act Density 0.432%

    No Known Activations