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
     wear
    -0.16
    ãĤ«ãĥ«
    -0.15
    ARGIN
    -0.15
    hdl
    -0.14
     worn
    -0.14
     unp
    -0.14
    idis
    -0.13
    icher
    -0.13
    .closed
    -0.13
     wearer
    -0.13
    POSITIVE LOGITS
     Census
    0.19
     accuracy
    0.18
     census
    0.17
     accur
    0.17
     Accuracy
    0.17
    Accuracy
    0.16
    accuracy
    0.16
     privacy
    0.16
    imas
    0.16
    Ware
    0.15
    Act Density 0.007%

    No Known Activations