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

    Neuronpedia

    INDEX
    Explanations

    references to justice and related concepts in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    プーン
    -0.63
    supp
    -0.54
    Rptr
    -0.53
     suppress
    -0.53
     vapeur
    -0.51
     doute
    -0.49
    htdocs
    -0.48
    둑
    -0.47
    Supp
    -0.47
    Ổ
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    1.19
     lip
    1.07
     justice
    1.05
     Sacrific
    0.96
    justice
    0.93
     PyLong
    0.92
     compromise
    0.91
    comprom
    0.89
     sacrifices
    0.88
     LIP
    0.86
    Act Density 0.074%

    No Known Activations