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

    Neuronpedia

    INDEX
    Explanations

    countable nouns preceded by words indicating a large quantity, such as "Thousands" and "Hundreds"

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people, specifically thousands or hundreds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     implied
    -0.77
     otherwise
    -0.74
     salad
    -0.72
     propri
    -0.71
     eval
    -0.69
     evaluation
    -0.68
     consistency
    -0.68
     regression
    -0.67
     homework
    -0.67
     overall
    -0.67
    POSITIVE LOGITS
    Thousands
    3.00
    Hundreds
    2.68
     Thousands
    2.42
     Hundreds
    2.23
     Dozens
    1.82
     Millions
    1.68
     Tens
    1.45
    ousands
    1.34
    zens
    1.34
    undreds
    1.29
    Act Density 0.029%

    No Known Activations