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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to sampling techniques and methodologies

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

    sampling schemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    -0.45
    <h1>
    -0.45
    /**
    -0.44
    Line
    -0.44
    ,
    -0.43
    Doctor
    -0.43
    <bos>
    -0.42
    -
    -0.42
    a
    -0.41
    WithFormat
    -0.41
    POSITIVE LOGITS
     MINING
    0.70
     Sampling
    0.69
     Mining
    0.67
    Shannon
    0.66
    Mining
    0.66
     Sourcing
    0.66
     foraging
    0.65
     SAMPLING
    0.65
    ICING
    0.64
     Shannon
    0.63
    Act Density 0.013%

    No Known Activations