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

    Neuronpedia

    INDEX
    Explanations

    instructions on how to perform specific technical tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.82
    argout
    -0.78
    +#+#
    -0.69
    WireFormatLite
    -0.59
    StoryboardSegue
    -0.58
    ViewImports
    -0.58
    ⓧ
    -0.57
    RectangleBorder
    -0.56
    KommentareTeilen
    -0.56
    }],
    -0.55
    POSITIVE LOGITS
     test
    0.97
     tests
    0.77
     Test
    0.77
     tested
    0.77
     testing
    0.76
    test
    0.72
    Test
    0.69
     TEST
    0.69
    TEST
    0.69
    测试
    0.67
    Act Density 0.919%

    No Known Activations