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

    Neuronpedia

    INDEX
    Explanations

    file paths or resource references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FB
    -0.17
    aque
    -0.15
    aida
    -0.15
    plib
    -0.15
    718
    -0.15
    baugh
    -0.15
    cken
    -0.15
    ustum
    -0.15
    arton
    -0.14
    ------+------+
    -0.14
    POSITIVE LOGITS
    bis
    0.16
    unca
    0.16
    -auto
    0.15
    upp
    0.15
    .xml
    0.14
    .android
    0.14
    ld
    0.14
    stoff
    0.14
    .attrib
    0.14
    .xz
    0.13
    Act Density 0.001%

    No Known Activations