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

    Neuronpedia

    INDEX
    Explanations

    inclusive language referencing diverse groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    consin
    -0.52
     <=",
    -0.50
    ligible
    -0.49
     nowrap
    -0.49
     clara
    -0.48
     Sti
    -0.47
    podes
    -0.47
    UTERS
    -0.46
    JsonFormat
    -0.46
     inform
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.77
     végét
    0.67
    ⓧ
    0.66
     تضيفلها
    0.65
    rophoresis
    0.64
    وعة
    0.63
     déput
    0.61
    +:+
    0.60
    StoreMessageInfo
    0.60
     ویکی‌پدیا
    0.59
    Act Density 0.093%

    No Known Activations