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

    Neuronpedia

    INDEX
    Explanations

    key legal terms and outcomes from court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :Any
    -0.18
    ARC
    -0.15
    ANY
    -0.15
     queryInterface
    -0.15
    ÏĦοκ
    -0.15
    taj
    -0.15
    _UNUSED
    -0.15
    .Paint
    -0.14
    icers
    -0.14
    arians
    -0.14
    POSITIVE LOGITS
    sville
    0.19
     Haw
    0.15
     Tensor
    0.15
     favour
    0.14
    ÑģÑĤÑĸ
    0.14
     favor
    0.14
    mine
    0.14
     Phonetic
    0.14
     Tits
    0.14
    iteur
    0.14
    Act Density 0.221%

    No Known Activations