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

    Neuronpedia

    INDEX
    Explanations

    references to arcade or gaming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to arcade games and gaming culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.81
    lying
    -0.74
    AKING
    -0.74
     Dalai
    -0.73
    ullah
    -0.68
    atche
    -0.68
    20439
    -0.66
    hood
    -0.65
    avering
    -0.64
    tons
    -0.64
    POSITIVE LOGITS
    regate
    0.91
    eers
    0.87
     arcade
    0.86
    yrinth
    0.84
     racer
    0.83
     cabinets
    0.81
    cade
    0.77
    eer
    0.76
    Pie
    0.75
    cephal
    0.73
    Act Density 0.009%

    No Known Activations