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

    Neuronpedia

    INDEX
    Explanations

    references to crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILayout
    -0.84
    parsedMessage
    -0.73
     ArrayAdapter
    -0.70
     wünscht
    -0.70
    PageFactory
    -0.67
     дописавши
    -0.67
    SpringBootTest
    -0.64
     définiti
    -0.63
     Wrang
    -0.63
    ValueStyle
    -0.63
    POSITIVE LOGITS
     crime
    1.81
     crimes
    1.69
     Crime
    1.61
     CRIME
    1.55
     Crimes
    1.51
    Crime
    1.47
     criminal
    1.45
    crime
    1.41
    crimes
    1.31
     crimen
    1.24
    Act Density 0.201%

    No Known Activations