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

    Neuronpedia

    INDEX
    Explanations

    summaries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "summary" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duct
    -0.76
    gypt
    -0.72
     charism
    -0.69
     Wee
    -0.66
    train
    -0.66
    enne
    -0.66
     Mouth
    -0.66
    bees
    -0.65
    Sea
    -0.65
    yss
    -0.63
    POSITIVE LOGITS
     summar
    0.90
     summarize
    0.88
     summ
    0.87
     thereof
    0.87
     summary
    0.79
     summarizes
    0.76
    krit
    0.76
     overview
    0.75
     synopsis
    0.72
    ostic
    0.72
    Act Density 0.051%

    No Known Activations