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

    Neuronpedia

    INDEX
    Explanations

    words related to computer performance and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to performance metrics in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shi
    -0.83
    cot
    -0.79
    ke
    -0.77
    bara
    -0.77
    bery
    -0.77
    cott
    -0.75
    oslov
    -0.70
    yu
    -0.69
    yg
    -0.68
    bin
    -0.68
    POSITIVE LOGITS
     enhancement
    1.02
     tuning
    0.98
     enhancing
    0.97
     improvement
    0.96
     optimization
    0.91
     optimizations
    0.89
     performance
    0.89
     enhancements
    0.88
     improvements
    0.87
    Performance
    0.86
    Act Density 0.017%

    No Known Activations