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

    Neuronpedia

    INDEX
    Explanations

    references to hidden or non-visible elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iga
    -0.17
    ilon
    -0.16
    oÄŁlu
    -0.15
    ALSE
    -0.15
    MSN
    -0.14
    онÑĮ
    -0.14
    ppelin
    -0.14
    oppins
    -0.14
    SelectionMode
    -0.14
     lug
    -0.14
    POSITIVE LOGITS
    azio
    0.15
     Comb
    0.14
    vious
    0.14
    rike
    0.14
    hid
    0.13
     GetCurrent
    0.13
    ãĤ¤ãĥī
    0.13
    ieux
    0.13
    emax
    0.13
    ikt
    0.13
    Act Density 0.002%

    No Known Activations