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

    Neuronpedia

    INDEX
    Explanations

    quantities expressed in scientific notation

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.57
     excelencia
    -0.56
    ]+$
    -0.54
    oredCriteria
    -0.54
     Keaton
    -0.53
    stå
    -0.52
    ignac
    -0.51
    clude
    -0.50
     chó
    -0.50
    accueil
    -0.50
    POSITIVE LOGITS
    $^{\
    3.53
    $^\
    0.94
    Datuak
    0.73
     consultato
    0.64
    ValueStyle
    0.62
     дописавши
    0.61
    Hozzáférés
    0.60
    发表于
    0.59
     lenker
    0.57
     ब्रेकडाउन
    0.56
    Act Density 0.003%

    No Known Activations