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

    Neuronpedia

    INDEX
    Explanations

    words related to music and various entities or concepts such as cameras, robots, and villains

    oai_token-act-pair · gpt-3.5-turbo

    references to movies and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ])
    -0.85
     )))
    -0.84
     )]
    -0.84
     ),
    -0.76
     ));
    -0.75
     ))
    -0.73
    ]),
    -0.72
     ):
    -0.70
    BuyableInstoreAndOnline
    -0.68
    20439
    -0.68
    POSITIVE LOGITS
    .
    1.26
    .?
    1.07
    .:
    0.91
    .;
    0.86
    _.
    0.84
    ./
    0.83
    ._
    0.83
    !.
    0.83
    .(
    0.82
    ."
    0.79
    Act Density 0.599%

    No Known Activations