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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duplication and repetition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duplication of data or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AFTA
    -0.76
    achine
    -0.71
    udder
    -0.71
    gamer
    -0.68
    burn
    -0.64
    riel
    -0.64
    TOR
    -0.63
    morning
    -0.62
    ther
    -0.61
    pour
    -0.60
    POSITIVE LOGITS
    icates
    1.08
     duplication
    0.99
    icative
    0.97
     duplicate
    0.96
     dupl
    0.94
    icated
    0.89
     negatives
    0.88
     Dupl
    0.81
     copies
    0.80
    liness
    0.78
    Act Density 0.017%

    No Known Activations