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

    Neuronpedia

    INDEX
    Explanations

    statements of opinion and expressions of personal beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transición
    -0.51
    SequentialGroup
    -0.46
     financieras
    -0.45
     réfugiés
    -0.44
    DockStyle
    -0.44
     CallOverrides
    -0.42
    IsMutable
    -0.42
     éxitos
    -0.42
    高质量
    -0.42
     arquitetura
    -0.41
    POSITIVE LOGITS
     moral
    0.69
     morally
    0.69
     justifiable
    0.59
     morals
    0.57
    moral
    0.56
     argument
    0.56
    Moral
    0.56
     justified
    0.54
     immoral
    0.54
     ethically
    0.54
    Act Density 0.794%

    No Known Activations