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

    Neuronpedia

    INDEX
    Explanations

    time-related events expressed through the word "shortly"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "shortly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.76
    elsen
    -0.72
    che
    -0.69
    ammy
    -0.67
    ictive
    -0.66
    iola
    -0.66
    lace
    -0.65
    GA
    -0.65
    eries
    -0.63
    raid
    -0.63
    POSITIVE LOGITS
     thereafter
    1.12
    mares
    0.95
    aneously
    0.85
    eteenth
    0.76
     afterwards
    0.73
     afterward
    0.70
     arriving
    0.70
    isode
    0.69
    cture
    0.68
     followed
    0.67
    Act Density 0.017%

    No Known Activations