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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     attendance
    -0.68
    enger
    -0.63
     availability
    -0.61
     prominently
    -0.60
     stakes
    -0.59
    emouth
    -0.59
     participation
    -0.57
     carriers
    -0.56
     dormant
    -0.55
     frequent
    -0.55
    POSITIVE LOGITS
     dx
    0.82
    06
    0.76
    075
    0.76
    07
    0.74
    05
    0.74
    04
    0.72
    1969
    0.72
    59
    0.71
    1959
    0.71
    09
    0.71
    Act Density 0.051%

    No Known Activations