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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "copy" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "copy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astical
    -0.81
    usalem
    -0.75
    ategory
    -0.73
    ESCO
    -0.71
     destro
    -0.71
    rontal
    -0.68
    Interstitial
    -0.68
    steamapps
    -0.65
    otor
    -0.63
    senal
    -0.62
    POSITIVE LOGITS
    writer
    1.01
    cat
    0.93
    sheet
    0.87
    writing
    0.87
     thereof
    0.86
     copy
    0.85
     paste
    0.84
     copies
    0.81
    sheets
    0.79
    writers
    0.79
    Act Density 0.021%

    No Known Activations