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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and instructions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to data processing and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brand
    -0.89
    enture
    -0.86
    mare
    -0.83
    trade
    -0.80
    ussen
    -0.77
    smoking
    -0.77
    audi
    -0.76
    ayne
    -0.76
    uro
    -0.76
    acre
    -0.75
    POSITIVE LOGITS
     automatically
    1.08
     output
    1.07
     dynamically
    0.99
     milliseconds
    0.98
     cached
    0.97
     json
    0.95
     JSON
    0.93
     caching
    0.91
     HTTP
    0.88
     backend
    0.88
    Act Density 0.323%

    No Known Activations