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

    Neuronpedia

    INDEX
    Explanations

    elements related to compliance and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.77
    ]--;
    -0.73
    }")
    -0.71
    ///</
    -0.71
     InputDecoration
    -0.71
    AxisAlignment
    -0.70
     تضيفلها
    -0.69
    EndInit
    -0.69
    protoimpl
    -0.69
    orianCalendar
    -0.67
    POSITIVE LOGITS
     terhadap
    0.61
     of
    0.55
     tunggal
    0.46
     refirió
    0.44
    おう
    0.43
     tästä
    0.42
     bebek
    0.40
     about
    0.40
     into
    0.39
     to
    0.38
    Act Density 0.690%

    No Known Activations