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

    Neuronpedia

    INDEX
    Explanations

    formatted or structured data, including visual separators and underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Callable
    -0.15
    alla
    -0.15
    eller
    -0.14
    prise
    -0.14
    elong
    -0.14
    lotte
    -0.14
    ýš
    -0.14
    outil
    -0.14
    ervals
    -0.14
    Äĥ
    -0.13
    POSITIVE LOGITS
    605
    0.17
    áºŃu
    0.17
     Kun
    0.15
    908
    0.15
    ±
    0.14
     BUG
    0.14
    paged
    0.14
    929
    0.13
    ibly
    0.13
     scrap
    0.13
    Act Density 0.005%

    No Known Activations