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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and references to guilty pleas in criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.91
    horn
    -0.80
    ãĥ¼ãĥ«
    -0.78
    ãĥ¼ãĤ¯
    -0.77
    ãĤª
    -0.75
    paces
    -0.73
    ãĤ£
    -0.73
    pace
    -0.73
    angular
    -0.73
    ãĤ«
    -0.72
    POSITIVE LOGITS
     perjury
    1.05
     manslaughter
    1.03
     felony
    0.99
     homicide
    0.97
     prosecution
    0.95
     criminally
    0.94
     felon
    0.92
    querque
    0.90
     extradition
    0.90
     treason
    0.88
    Act Density 0.358%

    No Known Activations