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

    Neuronpedia

    INDEX
    Explanations

    configurations and relationships among various elements or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thousands
    -0.52
     Thousands
    -0.50
     tens
    -0.50
    thousands
    -0.50
    Tens
    -0.49
     milliers
    -0.49
    Thousands
    -0.49
     millions
    -0.49
     Tens
    -0.48
     milhares
    -0.45
    POSITIVE LOGITS
     four
    2.06
     five
    1.86
     three
    1.85
    four
    1.76
     six
    1.75
     seven
    1.64
     eight
    1.63
    three
    1.63
     quatre
    1.62
    five
    1.59
    Act Density 0.882%

    No Known Activations