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

    Neuronpedia

    INDEX
    Explanations

    references to updates or changes in a system, emphasizing new features, integrations, or improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    州市
    -0.50
    getBase
    -0.39
    ruti
    -0.39
    getList
    -0.38
    ɜ
    -0.38
    UNITY
    -0.36
     getBase
    -0.36
    wara
    -0.36
    ürtel
    -0.36
    gné
    -0.36
    POSITIVE LOGITS
     new
    2.56
    new
    2.22
     newly
    2.01
     nuevos
    1.99
     nieuwe
    1.94
     nueva
    1.94
     nuevo
    1.91
     nouveaux
    1.86
     neuen
    1.85
     neue
    1.83
    Act Density 0.471%

    No Known Activations