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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to significant counts or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.18
    all
    -0.17
    edor
    -0.16
    hurst
    -0.16
    ance
    -0.16
    th
    -0.15
    ese
    -0.15
    airs
    -0.15
    places
    -0.15
    lah
    -0.15
    POSITIVE LOGITS
    st
    0.49
    ï¸ı
    0.35
    /XMLSchema
    0.26
    stin
    0.23
    âĢ³
    0.19
    sts
    0.19
    -й
    0.19
    -го
    0.19
    stu
    0.19
    Û°Û°
    0.18
    Act Density 0.313%

    No Known Activations