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

    Neuronpedia

    INDEX
    Explanations

    references to calculations or averaging data in a tabular format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clocks
    -0.17
    Timing
    -0.17
    Clock
    -0.16
    TimeString
    -0.16
     ÏĩÏģÏĮ
    -0.16
     Timing
    -0.15
     timing
    -0.15
    estruction
    -0.15
     timeout
    -0.15
    .Timeout
    -0.15
    POSITIVE LOGITS
     sales
    0.27
     Sales
    0.24
     rolling
    0.22
    sales
    0.21
     sale
    0.21
     Prev
    0.21
     lag
    0.21
    Sales
    0.21
     Previous
    0.21
     Cum
    0.20
    Act Density 0.010%

    No Known Activations