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

    Neuronpedia

    INDEX
    Explanations

    references to international collaboration and discussions on human resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RACT
    -0.18
    avra
    -0.17
    kün
    -0.15
    رب
    -0.14
    pard
    -0.14
     Mesh
    -0.14
    ucer
    -0.14
     ÑģÑĤек
    -0.14
     estates
    -0.14
    383
    -0.14
    POSITIVE LOGITS
     Party
    0.26
    Party
    0.22
     Ho
    0.19
     Vietnam
    0.18
    .vn
    0.18
    bach
    0.17
     Dak
    0.17
     Dien
    0.17
     viet
    0.17
    ynchronously
    0.17
    Act Density 0.011%

    No Known Activations