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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "copy" appears

    oai_token-act-pair · gpt-3.5-turbo

    references to obtaining or reproducing copies of various items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.73
    senal
    -0.69
    Interstitial
    -0.68
    doms
    -0.67
    OUN
    -0.67
    ailed
    -0.66
    ESCO
    -0.64
    ategory
    -0.63
    ricular
    -0.63
    ilitary
    -0.62
    POSITIVE LOGITS
     copy
    1.12
     copies
    1.01
    copy
    0.97
     Copy
    0.93
    cat
    0.85
    writer
    0.83
    cats
    0.82
    wright
    0.78
     paste
    0.78
    sheet
    0.77
    Act Density 0.012%

    No Known Activations