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

    Neuronpedia

    INDEX
    Explanations

    various instances and variations of the word "placeholder" in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bott
    -0.17
    nd
    -0.16
    shore
    -0.15
     pak
    -0.15
    pak
    -0.15
    ola
    -0.15
    ially
    -0.14
     Bah
    -0.14
    oui
    -0.14
     aggrav
    -0.14
    POSITIVE LOGITS
    رÛĮاÙĨ
    0.16
    ENUM
    0.15
    oppers
    0.14
    γι
    0.14
    attery
    0.14
    _DIRECT
    0.14
    gorm
    0.14
     ÑģÑĤаÑĢа
    0.14
    AffineTransform
    0.14
    vů
    0.13
    Act Density 0.003%

    No Known Activations