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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лаж
    -0.16
    /cms
    -0.16
    ĴĮ
    -0.15
    家çļĦ
    -0.15
    culus
    -0.15
    loth
    -0.15
     Feinstein
    -0.14
    .ms
    -0.14
     ÙħÛĮÚ©
    -0.14
    oldt
    -0.14
    POSITIVE LOGITS
    ½
    0.17
    353
    0.16
    ish
    0.14
    owing
    0.14
    325
    0.14
    ETY
    0.14
    IRS
    0.14
    gon
    0.14
     whopping
    0.13
    rd
    0.13
    Act Density 0.075%

    No Known Activations