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

    Neuronpedia

    INDEX
    Explanations

    references to randomness or chaotic occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptal
    -0.17
    odal
    -0.16
    irst
    -0.15
    inker
    -0.15
    ows
    -0.14
    IRST
    -0.14
    inerary
    -0.14
    indr
    -0.14
    omp
    -0.14
    imagenes
    -0.13
    POSITIVE LOGITS
    /random
    0.19
    ifi
    0.17
    iciel
    0.15
    s
    0.15
    aken
    0.15
    ised
    0.14
    ä¹±
    0.14
    Æ¡
    0.14
    evin
    0.14
     assortment
    0.14
    Act Density 0.019%

    No Known Activations