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

    Neuronpedia

    INDEX
    Explanations

    articles marked as "Continued Below" in a text document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "Article Continued Below."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SW
    -0.72
    RAW
    -0.67
    romy
    -0.67
    oka
    -0.66
    ring
    -0.65
    mini
    -0.63
     Rebellion
    -0.62
     FML
    -0.62
    MM
    -0.62
    sth
    -0.61
    POSITIVE LOGITS
     Loading
    0.66
     Thumbnails
    0.63
     Continue
    0.62
    etitive
    0.62
    ossus
    0.62
    guyen
    0.62
     suscept
    0.60
     fert
    0.59
     deploy
    0.59
    tics
    0.58
    Act Density 0.008%

    No Known Activations