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

    Neuronpedia

    INDEX
    Explanations

    dates and times mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of time and scheduling details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     emoji
    -0.90
     invading
    -0.83
    xual
    -0.81
     tro
    -0.81
     tyrann
    -0.80
     habit
    -0.80
     grop
    -0.80
    ĸļ
    -0.80
     ignor
    -0.80
     ul
    -0.79
    POSITIVE LOGITS
    Includes
    1.58
    October
    1.47
    November
    1.47
    January
    1.44
    September
    1.44
    December
    1.42
    August
    1.42
    February
    1.41
    Average
    1.41
    Leader
    1.41
    Act Density 0.174%

    No Known Activations