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

    Neuronpedia

    INDEX
    Explanations

    keywords related to lists, accounts, and resources within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -1.12
     ModelExpression
    -0.98
    SourceChecksum
    -0.91
     ویکی‌پدیا
    -0.89
    featureID
    -0.85
    ConstraintMaker
    -0.85
     esternos
    -0.81
    GEBURTSDATUM
    -0.79
     NSCoder
    -0.79
    CloseOperation
    -0.78
    POSITIVE LOGITS
     sous
    0.53
    zed
    0.49
    listdir
    0.49
    yy
    0.46
    mia
    0.43
    bia
    0.42
     claro
    0.42
    ksa
    0.41
    yyyy
    0.41
    참고
    0.41
    Act Density 0.026%

    No Known Activations