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

    Neuronpedia

    INDEX
    Explanations

    interrogative words and phrases used in questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldo
    -0.17
    _callable
    -0.15
    ercul
    -0.15
     Katz
    -0.15
     recip
    -0.14
    upt
    -0.14
    æ´ŀ
    -0.14
    ny
    -0.14
    -Ray
    -0.14
    .fixture
    -0.14
    POSITIVE LOGITS
    raman
    0.15
    initializer
    0.14
    ospace
    0.14
    rowsable
    0.13
     hab
    0.13
    °
    0.13
    OMPI
    0.13
    utters
    0.13
    миÑĤ
    0.13
     миÑĤ
    0.13
    Act Density 0.007%

    No Known Activations