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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.57
     iNdEx
    -0.56
    ECONDS
    -0.51
     onOptions
    -0.48
     generations
    -0.48
     fibres
    -0.47
     metres
    -0.47
     لیتر
    -0.47
     neutrons
    -0.46
    KEYCODE
    -0.45
    POSITIVE LOGITS
     minute
    0.67
     mile
    0.59
     hour
    0.57
    minute
    0.56
     year
    0.54
     pound
    0.53
     month
    0.52
     acre
    0.52
    +-
    0.51
    month
    0.50
    Act Density 0.562%

    No Known Activations