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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms, specifically mentioning the internet

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ');
    -0.88
    ");
    -0.74
    ":"/
    -0.65
    ").
    -0.65
    "],
    -0.65
    "...
    -0.64
    =#
    -0.63
    ema
    -0.62
    vale
    -0.61
    ',"
    -0.60
    POSITIVE LOGITS
     coupled
    1.39
     combined
    1.15
     including
    1.13
     namely
    1.07
     meanwhile
    1.04
     moreover
    1.01
     along
    1.00
     especially
    0.98
     albeit
    0.97
    particularly
    0.95
    Act Density 0.290%

    No Known Activations