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

    Neuronpedia

    INDEX
    Explanations

    dates and recurring events

    oai_token-act-pair · gpt-3.5-turbo

    references to occurrences or repetitions of events over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.69
    hift
    -0.63
    orce
    -0.60
    ering
    -0.60
    ordes
    -0.60
    osterone
    -0.60
    otyp
    -0.59
    ysis
    -0.59
    ription
    -0.59
    dinand
    -0.59
    POSITIVE LOGITS
     consecutive
    0.85
     anniversary
    0.76
     Anniversary
    0.63
     consecut
    0.63
     apiece
    0.59
    isodes
    0.59
     approvals
    0.58
     hiatus
    0.58
     tying
    0.58
    âĶĢ
    0.58
    Act Density 0.137%

    No Known Activations