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

    Neuronpedia

    INDEX
    Explanations

    topics related to legal disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coma
    -0.54
    انجليز
    -0.48
     scuole
    -0.47
    ржа
    -0.46
     tölt
    -0.46
    諌
    -0.45
    tsv
    -0.45
     beep
    -0.44
     rima
    -0.43
     Magen
    -0.43
    POSITIVE LOGITS
     Arbitrary
    0.96
     arbitrary
    0.94
     capricious
    0.87
    arbitrary
    0.84
     politici
    0.83
     arbitrar
    0.77
     arbitrarily
    0.76
     discriminatory
    0.73
     unfairly
    0.73
     uncons
    0.69
    Act Density 1.179%

    No Known Activations