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

    Neuronpedia

    INDEX
    Explanations

    elements of formal documentation and headings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahren
    -0.15
    unt
    -0.14
     reading
    -0.13
     newPos
    -0.13
    uit
    -0.13
     Tea
    -0.13
    iggins
    -0.13
    ility
    -0.13
    urls
    -0.13
    itor
    -0.13
    POSITIVE LOGITS
    arios
    0.16
    aits
    0.16
    hiba
    0.16
    caff
    0.15
    ighet
    0.15
    Containers
    0.15
    <location
    0.15
    енз
    0.15
    ruba
    0.14
    astle
    0.14
    Act Density 0.003%

    No Known Activations