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

    Neuronpedia

    INDEX
    Explanations

    concepts related to happiness and personal fulfillment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.61
    بوابة
    -0.56
     ویکی‌پدیا
    -0.54
     Савезне
    -0.53
    SharedCtor
    -0.52
    таратура
    -0.51
    łoni
    -0.49
     wireType
    -0.48
    nthetic
    -0.48
    Спасылкі
    -0.48
    POSITIVE LOGITS
     gift
    0.71
     gifts
    0.67
     voice
    0.64
     thread
    0.59
     Gifts
    0.58
     AttributeSet
    0.58
     humanity
    0.57
    InjectAttribute
    0.57
    scss
    0.56
    SourceChecksum
    0.55
    Act Density 0.330%

    No Known Activations