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

    Neuronpedia

    INDEX
    Explanations

    words related to values, principles, and concepts related to ethics and society

    oai_token-act-pair · gpt-3.5-turbo

    themes and concepts related to social values and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.92
    wic
    -0.87
     Printed
    -0.78
    azines
    -0.77
     Crusher
    -0.73
    letal
    -0.70
     IMAGES
    -0.68
    pps
    -0.66
    vertisements
    -0.66
    RN
    -0.66
    POSITIVE LOGITS
     openness
    1.46
     dignity
    1.44
     fairness
    1.44
     decency
    1.43
     equality
    1.41
     independence
    1.41
     prosperity
    1.41
     harmony
    1.36
     generosity
    1.34
     rationality
    1.32
    Act Density 0.190%

    No Known Activations