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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to random selection and sampling processes

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

    Probability calculations after sampling without replacement

    np_acts-logits-general · gemini-2.0-flash

    drawing without replacement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndInit
    -0.58
    ServletException
    -0.57
    putBoolean
    -0.54
     defaultstate
    -0.52
    SourceChecksum
    -0.51
    parsedMessage
    -0.51
    quelize
    -0.51
     kaarangay
    -0.51
    плуата
    -0.50
    ाषा
    -0.50
    POSITIVE LOGITS
     draw
    1.46
     lottery
    1.37
     draws
    1.30
     tirage
    1.27
     Draw
    1.23
     Lottery
    1.22
    draw
    1.20
     drawn
    1.20
     drawing
    1.16
     drew
    1.14
    Act Density 0.276%

    No Known Activations