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

    Neuronpedia

    INDEX
    Explanations

    references to policies or policy-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rita
    -0.15
    iest
    -0.15
    ussen
    -0.15
    bul
    -0.14
    bolt
    -0.14
    862
    -0.14
    à¹īà¸Ńà¸Ļ
    -0.14
    aylor
    -0.14
     jugg
    -0.14
    iness
    -0.14
    POSITIVE LOGITS
    holders
    0.18
    /legal
    0.15
    icc
    0.15
    ãĥĭãĥĥãĤ¯
    0.15
    ottle
    0.14
    oop
    0.14
    tester
    0.14
    ãĥ³ãĥĦ
    0.14
    hiba
    0.14
    holder
    0.14
    Act Density 0.038%

    No Known Activations