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

    Neuronpedia

    INDEX
    Explanations

    direct quotations from various sources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "quoted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achine
    -0.70
    wards
    -0.66
    amate
    -0.61
     Enh
    -0.60
     adulthood
    -0.59
    owl
    -0.59
     DARK
    -0.59
    ouple
    -0.59
    ful
    -0.59
    nect
    -0.57
    POSITIVE LOGITS
     quoted
    3.81
     cited
    2.19
     quotes
    2.13
     quoting
    2.07
     quote
    1.98
     quotations
    1.76
     quotation
    1.76
     referenced
    1.48
     reprinted
    1.45
     summarized
    1.43
    Act Density 0.008%

    No Known Activations