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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases expressing lack or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.77
     OFDb
    -0.58
     PeEnEo
    -0.56
    Personensuche
    -0.56
     otomatig
    -0.54
     fieldNum
    -0.53
    HtmlAttribute
    -0.52
     HasFactory
    -0.52
     purpoſe
    -0.52
     المعيارى
    -0.49
    POSITIVE LOGITS
     without
    0.40
     not
    0.37
     sé
    0.35
     Without
    0.33
    而不是
    0.33
     noqa
    0.33
     rather
    0.32
     zonder
    0.32
     bukan
    0.32
     regardless
    0.32
    Act Density 0.755%

    No Known Activations