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

    Neuronpedia

    INDEX
    Explanations

    dates or deadlines mentioned as the end of a period

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to deadlines and timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARI
    -0.71
     hindered
    -0.64
    OVA
    -0.62
     honor
    -0.61
     brewed
    -0.59
     raged
    -0.59
     fug
    -0.59
    erness
    -0.59
    ased
    -0.58
     cheered
    -0.58
    POSITIVE LOGITS
     2030
    0.86
     2025
    0.80
     2050
    0.78
     2021
    0.73
     2020
    0.71
    catentry
    0.70
    owment
    0.69
     constellation
    0.68
     reckoning
    0.68
    itiz
    0.68
    Act Density 0.039%

    No Known Activations