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

    Neuronpedia

    INDEX
    Explanations

    references to articles, discussions, and research reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sherman
    -0.14
    ÑĢок
    -0.13
    дÑĢ
    -0.13
    _nick
    -0.13
    LR
    -0.13
    .extension
    -0.13
    лиÑĤ
    -0.13
    owers
    -0.13
    light
    -0.13
    lef
    -0.13
    POSITIVE LOGITS
    innacle
    0.15
    ção
    0.15
    人人
    0.15
    æĪ
    0.15
    stroy
    0.14
    ¤¤
    0.14
    apse
    0.14
    boom
    0.14
    assa
    0.13
    aje
    0.13
    Act Density 0.741%

    No Known Activations