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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal rulings and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Abstractions
    -0.17
    ANS
    -0.17
     Colbert
    -0.14
    eneg
    -0.14
    anske
    -0.14
    رÙĥ
    -0.14
    iets
    -0.14
    /GPL
    -0.14
    Ø´ÛĮ
    -0.13
    omik
    -0.13
    POSITIVE LOGITS
     judgment
    0.30
     judgments
    0.28
     Lord
    0.26
     Judgment
    0.26
    Lord
    0.23
    heard
    0.23
     judgement
    0.21
     lord
    0.21
     heard
    0.21
     Lady
    0.20
    Act Density 0.045%

    No Known Activations