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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "few."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.97
    InjectAttribute
    -0.74
    RenderAtEndOf
    -0.71
    KURZBESCHREIBUNG
    -0.70
     مرئيه
    -0.69
    ⓧ
    -0.69
    RegressionTest
    -0.67
     ویکی‌پدیا
    -0.66
    TemporalType
    -0.65
     ProtoMessage
    -0.64
    POSITIVE LOGITS
     some
    0.83
     several
    0.81
     various
    0.66
     beberapa
    0.65
    several
    0.62
     slightly
    0.60
     algumas
    0.59
     just
    0.59
     many
    0.58
     algunas
    0.57
    Act Density 0.272%

    No Known Activations