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

    Neuronpedia

    INDEX
    Explanations

    legal or regulatory provisions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal provisions or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.71
    Magikarp
    -0.71
    ritz
    -0.67
    CV
    -0.66
    Pie
    -0.63
    rium
    -0.63
    Textures
    -0.62
     Carbuncle
    -0.61
    ampa
    -0.61
     Circus
    -0.59
    POSITIVE LOGITS
    witz
    1.15
    ality
    1.04
    ally
    1.00
    alities
    0.85
    ttes
    0.76
    arians
    0.75
    arian
    0.75
    ions
    0.74
     prohibiting
    0.74
     enacted
    0.74
    Act Density 0.043%

    No Known Activations