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

    Neuronpedia

    INDEX
    Explanations

    terms related to spirituality, morality, and religion

    oai_token-act-pair · gemini-2.0-flash

    divine concepts

    np_token-act-pair-logits · gpt-4o-mini

    Morality and ethics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //
    -0.86
     mauvaises
    -0.81
     mauva
    -0.80
     grève
    -0.80
     aveug
    -0.78
    ">//
    -0.77
     passés
    -0.75
     financières
    -0.75
     avoient
    -0.75
    GraphicsUnit
    -0.75
    POSITIVE LOGITS
     features
    0.52
     life
    0.50
     thought
    0.50
     thoughts
    0.50
     Ch
    0.48
    dom
    0.46
     e
    0.45
     J
    0.45
     cap
    0.45
    tissement
    0.45
    Act Density 3.217%

    No Known Activations