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

    Neuronpedia

    INDEX
    Explanations

    references to scientific or academic publications and their metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouro
    -0.16
    lasses
    -0.14
    ynchronously
    -0.14
    stractions
    -0.14
    itte
    -0.14
    utut
    -0.13
     happ
    -0.13
     çek
    -0.13
    adients
    -0.13
     اÙĦشخص
    -0.13
    POSITIVE LOGITS
    oyal
    0.14
     addCriterion
    0.14
    799
    0.14
    yne
    0.14
     Truman
    0.14
    tha
    0.14
     PAC
    0.14
    Pixel
    0.13
    ör
    0.13
     starving
    0.13
    Act Density 0.001%

    No Known Activations