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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authors and co-authors

    oai_token-act-pair · gpt-3.5-turbo

    references to authorship or co-authors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMS
    -0.76
     Pist
    -0.71
     wear
    -0.65
     Spears
    -0.64
     Leica
    -0.62
     Yard
    -0.62
     Maple
    -0.62
     Sabha
    -0.62
     Dortmund
    -0.61
    FW
    -0.61
    POSITIVE LOGITS
    itatively
    1.39
    itative
    1.17
    itarian
    1.04
    author
    0.98
    artist
    0.95
    itors
    0.94
    ournals
    0.92
    lisher
    0.91
    essee
    0.88
    alyst
    0.83
    Act Density 0.011%

    No Known Activations