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

    Neuronpedia

    INDEX
    Explanations

    statements related to legal proceedings, court cases, and rulings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     scenery
    -0.81
     journeys
    -0.81
     worsh
    -0.80
    escent
    -0.80
     util
    -0.79
     landscapes
    -0.79
     fascination
    -0.79
     humour
    -0.78
     friendships
    -0.77
     dips
    -0.77
    POSITIVE LOGITS
     Specifically
    1.24
     Lawyers
    1.24
     Officials
    1.19
     Judicial
    1.12
     Ultimately
    1.10
     However
    1.10
     Prosecutors
    1.09
     Previously
    1.09
     Essentially
    1.08
    Specifically
    1.07
    Act Density 0.470%

    No Known Activations