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

    Neuronpedia

    INDEX
    Explanations

    the beginning of the document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.66
     Wikimedijinoj
    -0.64
    UnusedPrivate
    -0.60
     <=",
    -0.58
    šinou
    -0.56
     helicópter
    -0.56
     subconsciously
    -0.55
     interchangeably
    -0.55
     efectivamente
    -0.55
    Vapour
    -0.55
    POSITIVE LOGITS
    <bos>
    1.42
    OGND
    0.65
    tvguidetime
    0.58
    Diwedd
    0.57
     الاطلاع
    0.57
    曖昧さ回避
    0.56
     Roskov
    0.55
     Waray
    0.55
     BorderRadius
    0.52
     незавершена
    0.52
    Act Density 0.266%

    No Known Activations