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

    Neuronpedia

    INDEX
    Explanations

    temporal sequences involving events happening on consecutive days

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "the next day."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.73
    ophon
    -0.66
    overe
    -0.65
    aden
    -0.62
    abilia
    -0.60
     Controls
    -0.60
    olen
    -0.59
    otto
    -0.59
    uckles
    -0.59
    pol
    -0.58
    POSITIVE LOGITS
    aneously
    0.80
    noon
    0.71
    nings
    0.67
     when
    0.67
    lier
    0.64
     afternoon
    0.64
    REP
    0.62
     commute
    0.62
    ItemThumbnailImage
    0.60
    cation
    0.60
    Act Density 0.057%

    No Known Activations