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

    Neuronpedia

    INDEX
    Explanations

    expressions related to legal or regulatory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.49
    ंदीखरीदारी
    -0.49
    SpringBootTest
    -0.48
    IUrlHelper
    -0.45
    :][
    -0.45
    antMatchers
    -0.44
    تقاوى
    -0.44
    WebVitals
    -0.43
    ագրություններ
    -0.43
    الدراسه
    -0.43
    POSITIVE LOGITS
     will
    0.68
     was
    0.67
     is
    0.65
     has
    0.60
     would
    0.58
     have
    0.57
     had
    0.54
     should
    0.54
     can
    0.53
     could
    0.51
    Act Density 0.653%

    No Known Activations