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

    Neuronpedia

    INDEX
    Explanations

    computer programming-related terms and code snippets within text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    0000000000000000
    -0.74
    owship
    -0.74
     Canaveral
    -0.71
    iasis
    -0.70
    toc
    -0.67
    according
    -0.67
    alle
    -0.66
    cise
    -0.66
    appiness
    -0.66
    cession
    -0.65
    POSITIVE LOGITS
    ĨĴ
    0.80
     conventions
    0.75
     convention
    0.73
    £ı
    0.73
     "$:/
    0.70
    uay
    0.65
     terminology
    0.64
    ĻĤ
    0.64
     Experiment
    0.63
     experimenting
    0.63
    Act Density 8.750%

    No Known Activations