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

    Neuronpedia

    INDEX
    Explanations

    words related to academic journals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scientific journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rises
    -0.71
     Afgh
    -0.70
    ugh
    -0.69
    BuyableInstoreAndOnline
    -0.66
    evil
    -0.64
    ghazi
    -0.62
    rav
    -0.62
    IDES
    -0.62
    forced
    -0.62
     Armored
    -0.61
    POSITIVE LOGITS
     journal
    1.45
     journals
    1.18
     Journals
    1.12
     papers
    1.06
    ournals
    1.03
    Paper
    0.94
    Journal
    0.88
     manuscript
    0.84
     paper
    0.84
     Papers
    0.84
    Act Density 0.012%

    No Known Activations