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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal relationships and past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    a time before something else

    np_acts-logits-general · gemini-2.0-flash

    before and prior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.73
    Personensuche
    -0.55
    뀜
    -0.47
    invokeLater
    -0.45
    enderror
    -0.45
     للاسماء
    -0.44
    ThemeOverlay
    -0.41
    ViewFeatures
    -0.40
    ایج
    -0.39
    MigrationBuilder
    -0.39
    POSITIVE LOGITS
     Previously
    0.79
    Previously
    0.79
     Before
    0.78
     vorher
    0.77
    Before
    0.77
     previously
    0.73
    before
    0.72
     Prior
    0.71
    Prior
    0.71
     before
    0.70
    Act Density 0.365%

    No Known Activations