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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating high rankings or elite status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iség
    -0.72
    Général
    -0.70
     AssemblyCompany
    -0.70
    loroethene
    -0.68
    huawei
    -0.63
    }')
    -0.63
    Ẽ
    -0.62
     gustó
    -0.62
    новниш
    -0.62
    rawdę
    -0.61
    POSITIVE LOGITS
     TOP
    2.09
     top
    1.96
     Top
    1.85
    TOP
    1.84
     tops
    1.81
    Top
    1.79
    top
    1.77
     Tops
    1.67
    getTop
    1.52
    tops
    1.45
    Act Density 0.076%

    No Known Activations