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

    Neuronpedia

    INDEX
    Explanations

    recent events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "recently."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utions
    -0.71
     whichever
    -0.70
     whatever
    -0.62
    ivery
    -0.60
     increments
    -0.58
    livion
    -0.58
     tion
    -0.56
    stract
    -0.55
     gratification
    -0.55
    absolute
    -0.55
    POSITIVE LOGITS
     recently
    3.51
     lately
    2.34
    recent
    2.23
     Recently
    2.03
    Recently
    1.99
     recent
    1.86
     previously
    1.66
     formerly
    1.38
     famously
    1.36
    Recent
    1.25
    Act Density 0.019%

    No Known Activations