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

    Neuronpedia

    INDEX
    Explanations

    phrases that inquire about the status or condition of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mahaman
    -0.52
     Ruskin
    -0.47
    choosing
    -0.46
    TestBed
    -0.46
     escrow
    -0.46
     defStyle
    -0.45
     Diſ
    -0.44
    휴
    -0.44
    ogaster
    -0.44
     Oswego
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.81
    yntaxException
    0.72
    还有什么
    0.70
    有沒有
    0.69
    有没有
    0.68
    İstinadlar
    0.66
    SharedDtor
    0.66
    potensi
    0.66
    Atsauces
    0.65
     فريبيس
    0.65
    Act Density 0.268%

    No Known Activations