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

    Neuronpedia

    INDEX
    Explanations

    legislation-related terms and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Passion
    -0.94
    angelo
    -0.68
     Atmosp
    -0.65
     virt
    -0.65
    sie
    -0.65
     Stronghold
    -0.65
     partName
    -0.65
    Sit
    -0.61
    inar
    -0.61
     Shang
    -0.61
    POSITIVE LOGITS
     protections
    1.09
     decriminal
    0.97
     exemptions
    0.93
     federally
    0.93
     repealed
    0.93
     amnesty
    0.91
     loopholes
    0.89
     legalized
    0.88
     outlaw
    0.86
     unconstitutional
    0.86
    Act Density 0.476%

    No Known Activations