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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer programming, specifically focusing on instructions, examples, and technical concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce explanations or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rodham
    -0.80
    AFP
    -0.73
     presided
    -0.64
     Guant
    -0.63
     kindred
    -0.61
     UNCLASSIFIED
    -0.60
     Salman
    -0.56
     Osama
    -0.55
    Putin
    -0.54
     Cheney
    -0.54
    POSITIVE LOGITS
    Example
    0.95
     drawback
    0.89
     downside
    0.82
     disadvantage
    0.79
     Example
    0.78
    oret
    0.78
     disadvantages
    0.77
     example
    0.74
    yip
    0.73
    entimes
    0.71
    Act Density 0.635%

    No Known Activations