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

    Neuronpedia

    INDEX
    Explanations

    times expressed in hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to time durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourke
    -0.80
    raviolet
    -0.73
    rique
    -0.72
    £ı
    -0.71
    prep
    -0.68
     Cutter
    -0.66
    opsy
    -0.64
    oÄŁ
    -0.64
    anke
    -0.64
    amaru
    -0.64
    POSITIVE LOGITS
     mins
    0.87
    lbs
    0.86
     lbs
    0.84
     ounces
    0.83
     grams
    0.83
     kW
    0.83
     pounds
    0.83
    61
    0.83
     minutes
    0.82
    76
    0.82
    Act Density 0.162%

    No Known Activations