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

    Neuronpedia

    INDEX
    Explanations

    structure-related commands or elements within scientific or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ista
    -0.15
    ìķ¡
    -0.15
     drain
    -0.15
    orks
    -0.14
    uss
    -0.14
    deniz
    -0.14
    PIX
    -0.13
     trap
    -0.13
    ADDE
    -0.13
    asi
    -0.13
    POSITIVE LOGITS
    agos
    0.16
    aison
    0.15
    vect
    0.15
    scaled
    0.15
    rana
    0.15
    ıs
    0.15
     closet
    0.15
    zı
    0.14
    ůl
    0.14
    زار
    0.14
    Act Density 0.016%

    No Known Activations