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

    Neuronpedia

    INDEX
    Explanations

    proposed changes or amendments in laws or policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to proposed laws and legal measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passion
    -0.69
     Divinity
    -0.66
    living
    -0.66
    EngineDebug
    -0.65
    UGH
    -0.65
    rete
    -0.64
    Being
    -0.62
     Riding
    -0.59
     Flying
    -0.59
     Indigo
    -0.59
    POSITIVE LOGITS
     prohibits
    1.14
     seeks
    1.13
     protects
    1.09
     allows
    1.08
     governs
    1.07
     forbids
    1.06
     restricts
    1.06
     prevents
    1.06
     resulted
    1.03
     establishes
    1.03
    Act Density 0.159%

    No Known Activations