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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "write" and its variations

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

    writing content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raborty
    -0.48
    sizePolicy
    -0.46
    XmlAccessType
    -0.46
    dbach
    -0.45
    [](
    -0.45
     McAfee
    -0.45
    Personensuche
    -0.45
     Meet
    -0.44
    )_{\
    -0.44
    />";
    -0.44
    POSITIVE LOGITS
     write
    1.23
    write
    1.11
     writing
    1.02
    Write
    1.02
     wrote
    0.99
     Write
    0.98
    wrote
    0.98
    written
    0.96
     WRITE
    0.96
     written
    0.92
    Act Density 0.016%

    No Known Activations