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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time, such as years, days of the week, and time-related words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "In [year]" or "On [day]" to signal specific events or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uminati
    -0.69
    psey
    -0.61
     Nug
    -0.59
    poke
    -0.58
    EngineDebug
    -0.58
    ocobo
    -0.58
    EStream
    -0.57
    ãĤ¨ãĥ«
    -0.56
     Albion
    -0.56
    etsy
    -0.56
    POSITIVE LOGITS
    entimes
    0.75
    sequently
    0.74
     latter
    0.73
     moreover
    0.65
     furthermore
    0.63
    anwhile
    0.62
     importantly
    0.60
     fict
    0.60
    Otherwise
    0.59
    beit
    0.59
    Act Density 0.851%

    No Known Activations