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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and titles, with a focus on movies and characters

    oai_token-act-pair · gpt-3.5-turbo

    references to popular cultural figures and entities, particularly related to entertainment and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.77
    minist
    -0.56
    pmwiki
    -0.55
    ãĤ¨ãĥ«
    -0.54
    ulative
    -0.51
    pedia
    -0.51
    afety
    -0.50
    DragonMagazine
    -0.50
    sectional
    -0.49
     Printed
    -0.49
    POSITIVE LOGITS
     etc
    0.92
    )).
    0.91
    )."
    0.88
    ]).
    0.87
    ).
    0.83
    ).[
    0.83
    ));
    0.82
    .).
    0.81
    ?).
    0.80
    }.
    0.78
    Act Density 1.631%

    No Known Activations