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

    Neuronpedia

    INDEX
    Explanations

    laws or principles

    oai_token-act-pair · gpt-3.5-turbo

    references to various laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittees
    -0.79
    staking
    -0.79
    20439
    -0.78
    Task
    -0.73
    NetMessage
    -0.72
    needed
    -0.72
     [&
    -0.71
    sites
    -0.70
     ILCS
    -0.69
    usercontent
    -0.69
    POSITIVE LOGITS
     physics
    0.93
     therm
    0.82
     evolution
    0.81
     propri
    0.79
     relativity
    0.77
     morality
    0.75
     rationality
    0.72
    ochemistry
    0.72
     gravity
    0.70
     physiology
    0.69
    Act Density 0.176%

    No Known Activations