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

    Neuronpedia

    INDEX
    Explanations

    references to sequences and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    la
    -0.18
    éĩı
    -0.16
    inez
    -0.16
    ucu
    -0.16
    teen
    -0.16
    land
    -0.15
    íĸ¥
    -0.15
    olas
    -0.15
    ina
    -0.15
    uts
    -0.15
    POSITIVE LOGITS
    urity
    0.18
    ively
    0.17
    unce
    0.17
     dÄ±ÅŁÄ±
    0.17
    ually
    0.16
    encing
    0.16
    ä¼į
    0.16
    hips
    0.15
    ardown
    0.15
    asar
    0.15
    Act Density 0.022%

    No Known Activations