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

    Neuronpedia

    INDEX
    Explanations

    references to chapters and page numbers in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _HINT
    -0.15
     Epoch
    -0.15
     اÙĦÙħÙĪس
    -0.15
    PEG
    -0.15
    Ñĥки
    -0.14
     Ñĥзн
    -0.14
    _DRIVE
    -0.14
    icari
    -0.14
    etti
    -0.14
     Bilg
    -0.14
    POSITIVE LOGITS
    eu
    0.15
    leigh
    0.15
    ogr
    0.15
     sang
    0.15
    ial
    0.14
     cling
    0.14
     Aw
    0.14
     novel
    0.13
    oran
    0.13
    åľŁ
    0.13
    Act Density 0.255%

    No Known Activations