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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or conditional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDIA
    -0.17
    nia
    -0.16
    ãĥĩãĥ«
    -0.14
    smarty
    -0.14
    gia
    -0.13
    subplot
    -0.13
    ılım
    -0.13
    olv
    -0.13
    ich
    -0.13
    atta
    -0.13
    POSITIVE LOGITS
     wondering
    0.16
     seems
    0.15
     obvious
    0.15
     ÑħоÑĤел
    0.15
     seem
    0.15
    ä¼¼ä¹İ
    0.15
    ãĥ¼ãĤº
    0.15
    uto
    0.15
     solutions
    0.14
     wonder
    0.14
    Act Density 0.077%

    No Known Activations