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

    Neuronpedia

    INDEX
    Explanations

    words related to legal cases and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    statements or facts related to legal rulings and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.78
    etheless
    -0.77
     seiz
    -0.71
     err
    -0.70
     Machina
    -0.63
     destruct
    -0.63
    uten
    -0.62
     pand
    -0.62
     citiz
    -0.61
    iencies
    -0.61
    POSITIVE LOGITS
    Interested
    0.85
    According
    0.83
    Specifically
    0.81
    Officials
    0.79
    WASHINGTON
    0.77
    Yesterday
    0.76
    Earlier
    0.75
    KR
    0.73
    Amid
    0.73
    Authorities
    0.72
    Act Density 0.162%

    No Known Activations