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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptions of measurements or distances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weeks
    -0.73
     weeks
    -0.72
     minutes
    -0.69
    weeks
    -0.69
    Weeks
    -0.68
     WEEKS
    -0.68
     months
    -0.67
     hours
    -0.66
    hrs
    -0.66
    Hours
    -0.66
    POSITIVE LOGITS
     hour
    0.59
     dollar
    0.58
     degree
    0.57
     pound
    0.52
     mile
    0.51
     year
    0.49
     month
    0.49
     acre
    0.49
     inch
    0.48
     minute
    0.47
    Act Density 0.428%

    No Known Activations