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

    Neuronpedia

    INDEX
    Explanations

    references to ethics and ethical committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ethics committee approval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeiti
    -0.50
    PreferredItem
    -0.48
     <<<<<<<<<<<<<<
    -0.46
    SequentialGroup
    -0.45
     Presently
    -0.44
     HttpNotFound
    -0.44
    ViewInit
    -0.44
    UrlResolution
    -0.43
    diğinde
    -0.43
    Kā
    -0.40
    POSITIVE LOGITS
     Ethics
    2.06
     ethics
    1.98
    Ethics
    1.92
    ethics
    1.80
     ethic
    1.16
     ética
    1.02
     morality
    0.94
     morals
    0.87
     Morality
    0.83
     Eth
    0.73
    Act Density 0.008%

    No Known Activations