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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical tests for heteroscedasticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    homoscedasticity and heteroskedasticity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grant
    -0.28
    aufnahme
    -0.28
    leyebilirsiniz
    -0.26
     سوز
    -0.25
     grant
    -0.25
    platz
    -0.25
     stripped
    -0.25
    flutter
    -0.24
    Clazz
    -0.23
     Sharp
    -0.23
    POSITIVE LOGITS
     betweenstory
    0.82
     nahilalakip
    0.82
    windowFixed
    0.79
    findpost
    0.75
    /*
    0.74
     surla
    0.70
     ujednoznacz
    0.69
    OGND
    0.67
    rawDesc
    0.67
    esgue
    0.67
    Act Density 0.409%

    No Known Activations