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

    Neuronpedia

    INDEX
    Explanations

    references to future events or actions indicated by the word "next."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interest
    -0.27
     Interest
    -0.24
    Interest
    -0.22
    interest
    -0.20
     interesse
    -0.19
     next
    -0.18
     näch
    -0.18
    _interest
    -0.16
    Next
    -0.16
    ouver
    -0.16
    POSITIVE LOGITS
     week
    0.30
     month
    0.29
     year
    0.29
    month
    0.23
     Woche
    0.19
    year
    0.19
    week
    0.19
    Month
    0.18
    YEAR
    0.17
    .year
    0.17
    Act Density 0.012%

    No Known Activations