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

    Neuronpedia

    INDEX
    Explanations

    references to classic works or masterpieces

    oai_token-act-pair · gpt-3.5-turbo

    references to classic films or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.70
     Frequency
    -0.67
     Impl
    -0.66
     Jensen
    -0.66
    nick
    -0.65
     uncontrolled
    -0.64
     sperm
    -0.63
     subdivision
    -0.63
     occupancy
    -0.62
     Jenn
    -0.62
    POSITIVE LOGITS
     classics
    2.99
     Classics
    2.22
    athered
    1.33
    eties
    1.24
    ellow
    1.17
     originals
    1.09
     legends
    1.05
     sage
    0.96
     staples
    0.95
     lame
    0.95
    Act Density 0.074%

    No Known Activations