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

    Neuronpedia

    INDEX
    Explanations

    words describing qualities or characteristics of products and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.16
    ãĥªãĥ¼ãĤº
    -0.15
    rike
    -0.15
    ÙĴس
    -0.15
    å¬
    -0.15
     Bes
    -0.14
    erk
    -0.14
    ÑĢÑĸд
    -0.14
    onto
    -0.14
    ias
    -0.14
    POSITIVE LOGITS
     enough
    0.23
    ä¸Ķ
    0.17
    izza
    0.15
    anked
    0.15
    .getDeclared
    0.15
    lich
    0.14
    agini
    0.14
    âĢĮترÛĮÙĨ
    0.14
     ترÛĮÙĨ
    0.14
    çļĦæĺ¯
    0.14
    Act Density 0.282%

    No Known Activations