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

    Neuronpedia

    INDEX
    Explanations

    references to entertainment industry publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of entertainment industry publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abases
    -0.75
    ophers
    -0.66
     labour
    -0.66
    ami
    -0.65
    built
    -0.63
     nonex
    -0.62
    earch
    -0.62
     robotic
    -0.61
    cies
    -0.60
    ebook
    -0.60
    POSITIVE LOGITS
     Variety
    1.38
     Pictures
    0.86
     Wrap
    0.83
    POST
    0.81
     Reporter
    0.79
     Features
    0.79
    iety
    0.77
     Deadline
    0.75
    Balance
    0.73
     Digest
    0.72
    Act Density 0.018%

    No Known Activations