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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, entities, or social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tres
    -0.17
    urnished
    -0.15
    openh
    -0.14
    á»ĵng
    -0.14
    ...',↵
    -0.14
    .assert
    -0.14
    ses
    -0.14
     beled
    -0.13
    oggler
    -0.13
     paddingBottom
    -0.13
    POSITIVE LOGITS
    official
    0.29
    83
    0.25
    88
    0.25
    1
    0.24
    89
    0.24
    87
    0.24
    79
    0.23
    84
    0.23
    Official
    0.23
    13
    0.23
    Act Density 0.082%

    No Known Activations