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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hour
    -0.31
    hour
    -0.30
     kilomet
    -0.29
     HOUR
    -0.28
     mile
    -0.28
    Hour
    -0.28
     metre
    -0.28
    minute
    -0.27
     Hour
    -0.27
     minute
    -0.26
    POSITIVE LOGITS
     units
    0.28
     bytes
    0.22
     fewer
    0.21
     cycles
    0.21
     feet
    0.20
     times
    0.20
     frames
    0.20
     seconds
    0.20
     inches
    0.20
     years
    0.19
    Act Density 0.396%

    No Known Activations