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

    Neuronpedia

    INDEX
    Explanations

    references to Uniform Resource Identifiers (URIs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼ĺ
    -0.16
    pires
    -0.15
    ook
    -0.15
     Hayward
    -0.15
    agne
    -0.15
    925
    -0.15
    zar
    -0.14
    ias
    -0.14
    fold
    -0.14
    IAS
    -0.14
    POSITIVE LOGITS
    sher
    0.15
    ÑĢид
    0.15
    dden
    0.15
    istine
    0.14
    0.14
    wang
    0.14
    istar
    0.14
    zÄĻ
    0.14
    idebar
    0.14
    ÑĥÑĢи
    0.13
    Act Density 0.024%

    No Known Activations