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

    Neuronpedia

    INDEX
    Explanations

    the character "Ċ" followed by single or double-digit numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     camp
    -0.73
     lifes
    -0.72
     swe
    -0.71
     commission
    -0.68
     tram
    -0.68
     bear
    -0.68
     bloc
    -0.68
     creature
    -0.68
     payroll
    -0.67
     covenant
    -0.67
    POSITIVE LOGITS
    However
    1.42
    Advertisement
    1.38
    Conclusion
    1.37
    Similarly
    1.36
    Moreover
    1.35
    Finally
    1.34
    Furthermore
    1.34
    Likewise
    1.34
    Nevertheless
    1.33
    Meanwhile
    1.32
    Act Density 0.654%

    No Known Activations