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

    Neuronpedia

    INDEX
    Explanations

    references to year-end summaries and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sted
    -0.15
     instant
    -0.14
    ernet
    -0.14
    jeme
    -0.14
     Sy
    -0.14
    ãĥ³
    -0.14
    icont
    -0.14
    olie
    -0.14
    fts
    -0.13
    uce
    -0.13
    POSITIVE LOGITS
    pio
    0.22
     Blasio
    0.17
    ãĤ¦ãĤ¹
    0.15
    alley
    0.14
     intermediate
    0.14
    arra
    0.14
    511
    0.14
    ::-
    0.14
    ало
    0.14
    .RowHeaders
    0.13
    Act Density 0.049%

    No Known Activations