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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating goals, intentions, or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OFDb
    -0.66
    ]--;
    -0.65
     otomatig
    -0.64
    omeness
    -0.64
     EconPapers
    -0.61
    ModelSerializer
    -0.61
    XtraEditors
    -0.59
     חיצוניים
    -0.57
     houſe
    -0.57
    URLException
    -0.57
    POSITIVE LOGITS
     here
    0.64
     then
    0.62
     ThemeData
    0.58
     daarbij
    0.58
     now
    0.55
     entonces
    0.54
     throughout
    0.54
     allora
    0.54
     siempre
    0.52
     isto
    0.52
    Act Density 0.256%

    No Known Activations