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

    Neuronpedia

    INDEX
    Explanations

    references to the term "original" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.68
    PerformLayout
    -0.68
    ValueStyle
    -0.61
    saraba
    -0.58
    THINGS
    -0.57
    verwijspagina
    -0.56
    #+#
    -0.56
    rawDesc
    -0.55
    webElementXpaths
    -0.54
    <blockquote>
    -0.54
    POSITIVE LOGITS
     Original
    0.93
    Original
    0.90
     ORIGINAL
    0.86
    ORIGINAL
    0.84
     orig
    0.79
     original
    0.79
     originals
    0.77
    原
    0.75
    original
    0.74
    getOriginal
    0.74
    Act Density 0.131%

    No Known Activations