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

    Neuronpedia

    INDEX
    Explanations

    occurrences of variable or placeholder syntax in code

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

    nginx configuration variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.75
     Garr
    -0.50
     Graff
    -0.48
     Bork
    -0.47
    !*\
    -0.46
     Kell
    -0.45
     Cartwright
    -0.45
     "
    -0.45
     Barnard
    -0.45
     Blair
    -0.44
    POSITIVE LOGITS
    ${
    1.74
    >${
    0.80
    ">${
    0.75
    ="${
    0.74
    "${
    0.73
    _${
    0.71
    }${
    0.69
    -${
    0.67
    :${
    0.67
    =${
    0.65
    Act Density 0.015%

    No Known Activations