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

    Neuronpedia

    INDEX
    Explanations

    the word "limited" with varying degrees of emphasis or relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashington
    -0.81
    tha
    -0.73
    CENT
    -0.71
    HEAD
    -0.69
    lyn
    -0.69
    NOR
    -0.68
    Oak
    -0.68
    ilon
    -0.67
    Mount
    -0.67
    mol
    -0.67
    POSITIVE LOGITS
     minded
    0.88
    inous
    0.85
     amount
    0.82
     amounts
    0.79
     collateral
    0.78
     exceptions
    0.77
     liability
    0.75
     lifespan
    0.74
     editions
    0.73
    restricted
    0.72
    Act Density 0.028%

    No Known Activations