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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions related to sign patterns and statistical functions in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mergeFrom
    -0.45
     économies
    -0.43
    getragen
    -0.43
     pouvoit
    -0.42
     competitivos
    -0.42
    reach
    -0.42
    뀔
    -0.42
    reaching
    -0.41
     فريبيس
    -0.41
     enfans
    -0.41
    POSITIVE LOGITS
     gender
    0.66
    gender
    0.58
     Gender
    0.54
    HtmlAttribute
    0.54
    性别
    0.52
    GENDER
    0.52
    /**
    0.50
    Gender
    0.49
    Jeografia
    0.49
    DrawerToggle
    0.47
    Act Density 1.141%

    No Known Activations