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

    Neuronpedia

    INDEX
    Explanations

    references to hyperlinks and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Safe
    -0.15
    irim
    -0.15
    ãĤĵãģ¨
    -0.14
    iran
    -0.14
    ÃľR
    -0.14
     Denise
    -0.14
     تÙģ
    -0.14
    GridColumn
    -0.14
     Stout
    -0.14
    senal
    -0.14
    POSITIVE LOGITS
    argas
    0.15
    ocket
    0.15
    .minecraft
    0.15
    arer
    0.15
     rhe
    0.14
     Higgins
    0.14
    omo
    0.14
    obo
    0.14
    usto
    0.14
     agr
    0.14
    Act Density 0.006%

    No Known Activations