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

    Neuronpedia

    INDEX
    Explanations

    phrases involving authors collaborating on writing or creating something, along with specific parts of documents, such as credits or acknowledgments

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that indicate collaboration or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wings
    -0.76
     currency
    -0.67
    reality
    -0.66
    isks
    -0.64
    blocks
    -0.63
    bread
    -0.62
    bucks
    -0.62
    abus
    -0.62
    wcs
    -0.62
    tera
    -0.62
    POSITIVE LOGITS
     Patrick
    1.10
     Shawn
    1.07
     Juan
    1.07
     Samuel
    1.07
     Andrew
    1.06
     Kevin
    1.05
     Kenneth
    1.05
     Jesse
    1.04
     Buster
    1.04
     William
    1.03
    Act Density 0.146%

    No Known Activations