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

    Neuronpedia

    INDEX
    Explanations

    references to software development and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and references to technical concepts or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     headlights
    -0.68
    DERR
    -0.64
     flares
    -0.64
     caution
    -0.64
     nods
    -0.63
    steen
    -0.63
    assetsadobe
    -0.62
     excuses
    -0.59
     scares
    -0.59
     critiques
    -0.58
    POSITIVE LOGITS
     sector
    0.78
    ourse
    0.78
     universe
    0.73
     region
    0.68
    osphere
    0.67
     ecosystem
    0.64
     arena
    0.63
     market
    0.63
     subsystem
    0.63
     area
    0.62
    Act Density 0.977%

    No Known Activations