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

    Neuronpedia

    INDEX
    Explanations

    phrases related to principles or values

    oai_token-act-pair · gpt-3.5-turbo

    references to principles or values, particularly in relation to societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.90
     istg
    -0.89
    reau
    -0.78
    REF
    -0.75
    banks
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
    LY
    -0.71
    Enlarge
    -0.70
    Effects
    -0.70
    monton
    -0.70
    POSITIVE LOGITS
     globalization
    0.86
     modern
    0.82
     everyday
    0.81
     capitalism
    0.79
     civilization
    0.78
     humankind
    0.78
     incumb
    0.77
     warfare
    0.76
     persuasion
    0.76
     academia
    0.75
    Act Density 0.235%

    No Known Activations