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

    Neuronpedia

    INDEX
    Explanations

    words related to regulation or controlling actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulation and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spell
    -0.71
    2019
    -0.67
     Zeal
    -0.67
    swick
    -0.67
    Bone
    -0.67
    peak
    -0.67
     Falcons
    -0.66
     Saints
    -0.65
    caps
    -0.65
     Mehran
    -0.64
    POSITIVE LOGITS
    ategory
    1.02
     regulates
    1.01
     regulate
    1.00
     regulating
    0.98
     regulated
    0.98
    ourgeois
    0.93
     governing
    0.89
     unregulated
    0.81
     violations
    0.81
    ively
    0.79
    Act Density 0.010%

    No Known Activations