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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to time intervals or financial figures

    oai_token-act-pair · gpt-3.5-turbo

    references to annual metrics or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holes
    -0.90
     Handler
    -0.88
    wright
    -0.82
    UTF
    -0.74
     Parad
    -0.73
    hole
    -0.72
    geist
    -0.69
    ymes
    -0.68
    kef
    -0.66
    words
    -0.66
    POSITIVE LOGITS
    ized
    0.99
    ãĥ¼ãĥĨãĤ£
    0.90
    ised
    0.88
    è¦ļéĨĴ
    0.79
     census
    0.79
     annual
    0.77
    ãĥ£
    0.72
     occurrence
    0.72
     appropriations
    0.72
     yearly
    0.71
    Act Density 0.014%

    No Known Activations