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

    Neuronpedia

    INDEX
    Explanations

    references to statistical values or measurements

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

    value and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
     Schne
    -0.52
     Schrö
    -0.51
    <h1>
    -0.51
     Humphreys
    -0.50
     McDermott
    -0.49
     McManus
    -0.49
     Broder
    -0.49
     McKnight
    -0.48
     main
    -0.46
    POSITIVE LOGITS
     Value
    1.16
     value
    1.12
    Value
    1.10
     Values
    1.04
     VALUE
    1.02
    value
    1.02
     값
    0.98
     getValue
    0.98
     values
    0.97
    值
    0.96
    Act Density 0.038%

    No Known Activations