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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their affiliations or attributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hare
    -0.67
    uyomi
    -0.66
     Yak
    -0.62
    vik
    -0.61
     Disciple
    -0.60
     cav
    -0.59
     gravy
    -0.58
     Rivals
    -0.58
     fruitful
    -0.58
     Dino
    -0.57
    POSITIVE LOGITS
    ]);
    0.93
     });
    0.84
    NPR
    0.81
    });
    0.77
    )</
    0.75
     Photography
    0.73
    ));
    0.73
    )."
    0.72
     ));
    0.68
    %).
    0.67
    Act Density 0.106%

    No Known Activations