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

    Neuronpedia

    INDEX
    Explanations

    attributes associated with ethical and moral values

    oai_token-act-pair · gpt-3.5-turbo

    commas in lists of ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riber
    -0.71
    cients
    -0.71
    cko
    -0.70
    acent
    -0.69
    quet
    -0.69
    upiter
    -0.68
    utor
    -0.68
    ported
    -0.67
    geon
    -0.67
    assed
    -0.67
    POSITIVE LOGITS
     creativity
    1.03
     albeit
    0.99
     heroism
    0.94
     humility
    0.92
     degradation
    0.92
     alienation
    0.89
     intolerance
    0.88
     tolerance
    0.87
     paranoia
    0.86
     bravery
    0.85
    Act Density 0.355%

    No Known Activations