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

    Neuronpedia

    INDEX
    Explanations

    references to the word "original" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mere
    -0.16
    aggable
    -0.16
     recent
    -0.16
    arine
    -0.16
    untu
    -0.15
    cken
    -0.14
    ua
    -0.14
    agged
    -0.14
     Wagner
    -0.14
    aul
    -0.14
    POSITIVE LOGITS
    /original
    0.26
    ity
    0.22
    arily
    0.21
    mente
    0.20
    -fashioned
    0.18
    isé
    0.17
    arity
    0.17
    ë¶ĢíĦ°
    0.17
    -language
    0.17
    ised
    0.16
    Act Density 0.030%

    No Known Activations