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

    Neuronpedia

    INDEX
    Explanations

    mentions of software updates and new features in tech products

    oai_token-act-pair · gpt-3.5-turbo

    mentions of software updates and their new features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mort
    -0.79
    boys
    -0.78
    hammer
    -0.76
    sal
    -0.76
    bell
    -0.74
    hus
    -0.74
    lie
    -0.73
    ogie
    -0.72
    cakes
    -0.71
    Lago
    -0.71
    POSITIVE LOGITS
     optimizations
    1.31
     APIs
    1.20
     functionality
    1.19
     compatibility
    1.19
     seamless
    1.16
     asynchronous
    1.15
     enhancements
    1.14
     improved
    1.13
     enhanced
    1.12
     integration
    1.11
    Act Density 0.321%

    No Known Activations