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

    Neuronpedia

    INDEX
    Explanations

    references to legal sentences and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.18
    ÏĢά
    -0.16
    esty
    -0.16
    ness
    -0.15
     Grat
    -0.15
    ç·Ĵ
    -0.15
    oded
    -0.15
     Mellon
    -0.15
    ly
    -0.15
    ORN
    -0.14
    POSITIVE LOGITS
    inals
    0.20
    355
    0.16
    apel
    0.15
    ments
    0.15
    urrect
    0.14
    325
    0.14
    inel
    0.14
    ourcem
    0.14
    iment
    0.14
    geber
    0.14
    Act Density 0.011%

    No Known Activations