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

    Neuronpedia

    INDEX
    Explanations

    timestamps related to events or durations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "period" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cole
    -0.65
    ply
    -0.65
    found
    -0.65
    ÄŁ
    -0.64
    RAY
    -0.61
    Always
    -0.61
    ILLE
    -0.61
    cart
    -0.61
    rious
    -0.61
    XY
    -0.61
    POSITIVE LOGITS
    icals
    1.14
     periods
    1.12
    ional
    0.98
    ftime
    0.95
    icity
    0.89
    period
    0.86
    ical
    0.85
    iday
    0.83
     period
    0.82
    oths
    0.81
    Act Density 0.033%

    No Known Activations