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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical changes or adjustments in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.81
     Italijanski
    -0.76
    Personendaten
    -0.75
    Vidite
    -0.69
    Geplaatst
    -0.67
     فريبيس
    -0.65
     Administrativna
    -0.63
     Réponses
    -0.62
    contentLoaded
    -0.62
     EconPapers
    -0.61
    POSITIVE LOGITS
     to
    0.67
     вд
    0.57
     dramatically
    0.55
     drastically
    0.54
     significantly
    0.50
    เหลือ
    0.50
     menjadi
    0.50
     slightly
    0.49
     below
    0.49
     by
    0.49
    Act Density 0.598%

    No Known Activations