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

    Neuronpedia

    INDEX
    Explanations

    questions directed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    questions directed at the reader that contain a form of "do you have" or "would you".

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     Jefus
    -0.71
     itſelf
    -0.69
     Lave
    -0.61
    তথ্যসূত্র
    -0.61
     needn
    -0.60
     Efq
    -0.60
     verfü
    -0.59
     houſe
    -0.58
     becauſe
    -0.58
     greateſt
    -0.57
    POSITIVE LOGITS
    UserScript
    0.79
     TextInputType
    0.75
     Graff
    0.72
    toHaveBeenCalled
    0.70
     Geller
    0.67
     Duckworth
    0.67
    BETH
    0.67
    ทร
    0.66
    ียด
    0.66
    uxxxx
    0.65
    Act Density 0.082%

    No Known Activations