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

    Neuronpedia

    INDEX
    Explanations

    articles and adjectives that indicate quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oku
    -0.17
    odore
    -0.16
    cente
    -0.15
    obb
    -0.15
    rea
    -0.15
    owo
    -0.14
    otti
    -0.14
    otype
    -0.14
    pire
    -0.14
    im
    -0.14
    POSITIVE LOGITS
     few
    0.20
    edis
    0.17
     certain
    0.17
     Certain
    0.17
     Few
    0.17
    ué
    0.16
    IData
    0.16
    upy
    0.15
    RT
    0.15
    anko
    0.14
    Act Density 0.135%

    No Known Activations