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

    Neuronpedia

    INDEX
    Explanations

    coding terms and functions related to software development

    oai_token-act-pair · gpt-3.5-turbo

    programming-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mole
    -0.70
     playthrough
    -0.69
     airs
    -0.65
     erased
    -0.65
     assassinated
    -0.62
     gearing
    -0.61
     wiping
    -0.60
     spinach
    -0.59
     dashed
    -0.59
     unpop
    -0.59
    POSITIVE LOGITS
     import
    1.02
    utils
    0.96
    Module
    0.95
    framework
    0.92
    common
    0.91
    import
    0.90
    Sharp
    0.89
    Reader
    0.88
    Engine
    0.86
    Factory
    0.85
    Act Density 0.058%

    No Known Activations