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

    Neuronpedia

    INDEX
    Explanations

    references to creative artistic works, such as songs, books, movies, and games

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic works, such as songs, films, and books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.74
    soever
    -0.72
    sbm
    -0.64
     PsyNet
    -0.62
    ECA
    -0.62
     sqor
    -0.61
    Interested
    -0.60
     Helpful
    -0.60
    ————
    -0.60
    artisan
    -0.60
    POSITIVE LOGITS
     itself
    1.31
     underwent
    1.03
     revolves
    1.00
     lasted
    0.99
     originated
    0.98
     boasts
    0.98
     culmin
    0.97
     lacks
    0.96
     became
    0.94
     debuted
    0.94
    Act Density 0.372%

    No Known Activations