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

    Neuronpedia

    INDEX
    Explanations

    references to specific durations of time in hours

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, particularly in hours

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AGA
    -0.69
     stabil
    -0.65
     gener
    -0.65
     prob
    -0.63
     neutral
    -0.63
     Native
    -0.61
     666
    -0.60
     general
    -0.60
     dece
    -0.59
     backwards
    -0.58
    POSITIVE LOGITS
    hour
    3.77
    Hour
    2.51
    hours
    2.39
     hour
    2.34
     Hour
    2.06
    minute
    1.84
     hours
    1.76
    Hours
    1.73
     Hours
    1.73
    day
    1.59
    Act Density 0.008%

    No Known Activations