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

    Neuronpedia

    INDEX
    Explanations

    terms related to technological performance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of performance metrics in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shi
    -0.90
    bery
    -0.81
    yu
    -0.78
    yg
    -0.75
    bara
    -0.75
    idan
    -0.73
    sonian
    -0.72
    bin
    -0.71
    cott
    -0.71
    ovie
    -0.69
    POSITIVE LOGITS
     enhancement
    1.00
     improvement
    0.98
     enhancing
    0.95
     optimization
    0.92
     degradation
    0.91
     tuning
    0.90
     improvements
    0.87
     optimizations
    0.87
     performance
    0.86
    Performance
    0.86
    Act Density 0.018%

    No Known Activations