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

    Neuronpedia

    INDEX
    Explanations

    references to surveys and data presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fts
    -0.19
    132
    -0.16
    omp
    -0.15
    owie
    -0.15
     fro
    -0.15
     meaning
    -0.15
    å¼
    -0.14
    ensed
    -0.14
     sure
    -0.14
     {↵
    -0.14
    POSITIVE LOGITS
    /Gate
    0.15
    ÙĪع
    0.14
    leck
    0.14
     tùy
    0.14
    ellow
    0.14
    алом
    0.14
     ê°ķëĤ¨
    0.14
     Berry
    0.14
    âĢĮاÙĨبار
    0.14
    оли
    0.14
    Act Density 0.156%

    No Known Activations