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

    Neuronpedia

    INDEX
    Explanations

    statements regarding transparency and accountability in decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cherchés
    -1.14
     initComponents
    -0.84
    UserScript
    -0.83
     للمعارف
    -0.82
    IsMutable
    -0.79
     disambiguazione
    -0.78
    HasAnnotation
    -0.75
     الدولى
    -0.74
     الرياضيه
    -0.74
     виправивши
    -0.73
    POSITIVE LOGITS
     arguments
    0.50
     review
    0.49
     prospect
    0.47
     before
    0.45
     negative
    0.45
     virgin
    0.44
     convince
    0.44
     prospective
    0.43
    평
    0.43
     concerns
    0.43
    Act Density 0.493%

    No Known Activations