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

    Neuronpedia

    INDEX
    Explanations

    dates and date ranges

    oai_token-act-pair · gpt-3.5-turbo

    date ranges and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     distingu
    -0.71
     crocod
    -0.69
     subscript
    -0.65
     divers
    -0.64
     glim
    -0.63
    ocus
    -0.63
     robber
    -0.63
     republican
    -0.62
     dinosaurs
    -0.61
     orcs
    -0.61
    POSITIVE LOGITS
     September
    1.33
    September
    1.33
     August
    1.31
     October
    1.30
    ember
    1.30
    June
    1.28
    October
    1.28
    November
    1.28
     July
    1.28
     June
    1.26
    Act Density 0.097%

    No Known Activations