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

    Neuronpedia

    INDEX
    Explanations

    numeric data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eighty
    -0.89
     seventy
    -0.88
     Thirty
    -0.87
     forty
    -0.85
     sixty
    -0.85
     fifty
    -0.84
    thirty
    -0.84
     Forty
    -0.83
     Seventy
    -0.82
     thirty
    -0.81
    POSITIVE LOGITS
     five
    0.92
     four
    0.92
    Three
    0.91
     three
    0.90
     Three
    0.89
    Five
    0.88
    three
    0.88
    THREE
    0.85
     Five
    0.85
     Four
    0.84
    Act Density 0.591%

    No Known Activations