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

    Neuronpedia

    INDEX
    Explanations

    terms related to duplicating or copying

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duplication and duplicate content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riel
    -0.76
    achine
    -0.73
    anwhile
    -0.72
    nee
    -0.72
    orsi
    -0.71
    gamer
    -0.71
    liner
    -0.68
    robe
    -0.67
    gold
    -0.67
    ther
    -0.67
    POSITIVE LOGITS
     duplication
    1.16
     dupl
    1.11
     duplicate
    1.10
    icates
    0.99
     negatives
    0.92
    icative
    0.91
     copies
    0.89
     Dupl
    0.86
     likeness
    0.77
    icated
    0.73
    Act Density 0.006%

    No Known Activations