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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government announcements or regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    marginHorizontal
    -0.72
    marginVertical
    -0.61
    paddingVertical
    -0.60
    paddingLeft
    -0.59
     marginBottom
    -0.58
    resizeMode
    -0.57
    OptionPane
    -0.55
    alignSelf
    -0.54
    TestTools
    -0.52
    CardBody
    -0.51
    POSITIVE LOGITS
     WHITE
    1.16
     White
    1.11
     white
    1.10
    white
    1.09
    White
    1.08
    WHITE
    1.03
     whites
    0.94
     Whites
    0.92
     whiteness
    0.91
     WHIT
    0.88
    Act Density 0.072%

    No Known Activations