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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming code elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.80
     Bravo
    -0.71
    emale
    -0.68
     Vaugh
    -0.66
    enegger
    -0.63
     Ezek
    -0.63
     advoc
    -0.62
     Indust
    -0.61
     Bust
    -0.59
     Madonna
    -0.59
    POSITIVE LOGITS
    ¶
    1.07
     parser
    1.01
     namespace
    0.96
     initialization
    0.96
     async
    0.93
     pointer
    0.91
     integer
    0.89
     shader
    0.89
     JSON
    0.88
     filesystem
    0.87
    Act Density 1.055%

    No Known Activations