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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or regulatory actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.78
    marginVertical
    -0.58
    EventQueue
    -0.57
     incarcer
    -0.56
    donc
    -0.56
    marginHorizontal
    -0.56
    setOpaque
    -0.56
    جغرافيا
    -0.54
     avoit
    -0.51
    BeginContext
    -0.51
    POSITIVE LOGITS
     religione
    0.68
     liev
    0.67
    any
    0.62
     scienza
    0.62
     ciga
    0.61
     borsa
    0.59
     medes
    0.59
     levis
    0.58
     ananas
    0.58
     kokos
    0.56
    Act Density 0.605%

    No Known Activations