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

    Neuronpedia

    INDEX
    Explanations

    concepts related to technology advancements and innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.71
     Réponses
    -0.66
     Monfieur
    -0.61
     للاسماء
    -0.60
    continence
    -0.60
    <bos>
    -0.58
    RegressionTest
    -0.56
    ()]);
    -0.56
    ModelSerializer
    -0.56
    upsi
    -0.55
    POSITIVE LOGITS
     popularity
    1.32
     popular
    1.22
    popular
    1.07
    Popular
    1.00
     trend
    0.99
    popularity
    0.98
     popularidad
    0.96
     Popularity
    0.95
     Popular
    0.94
     популяр
    0.92
    Act Density 0.723%

    No Known Activations