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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal terms or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal provisions or clauses in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     temperament
    -0.66
    Magikarp
    -0.65
     Doodle
    -0.64
    psy
    -0.64
    ampa
    -0.64
    ritz
    -0.64
    CV
    -0.63
     Ashes
    -0.62
     palms
    -0.60
    arton
    -0.59
    POSITIVE LOGITS
    ally
    1.12
    ality
    1.08
    witz
    0.99
    alities
    0.94
    ional
    0.92
    arians
    0.85
    arian
    0.84
    mental
    0.77
    ions
    0.77
    utical
    0.76
    Act Density 0.023%

    No Known Activations