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

    Neuronpedia

    INDEX
    Explanations

    references to census data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rome
    -0.17
     rub
    -0.15
    ome
    -0.15
    x
    -0.14
    ewe
    -0.14
     Nom
    -0.14
    romo
    -0.13
    ty
    -0.13
     cadena
    -0.13
    avs
    -0.13
    POSITIVE LOGITS
     verileri
    0.17
    .gov
    0.16
    imb
    0.15
    ãĥ¯ãĥ¼
    0.14
     ******************************************************************************/↵
    0.14
    owns
    0.14
    atori
    0.14
    mux
    0.14
    imator
    0.14
    emer
    0.14
    Act Density 0.009%

    No Known Activations