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

    Neuronpedia

    INDEX
    Explanations

    phrases that express expectations or conditions

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

    should + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.53
     ويكيميديا
    -0.50
     للمعارف
    -0.49
     Paglinawan
    -0.49
    ỡng
    -0.48
     चीज़ों
    -0.43
     revés
    -0.42
     zagran
    -0.42
    зможно
    -0.41
     KeyError
    -0.41
    POSITIVE LOGITS
    should
    0.95
    Should
    0.68
     Should
    0.67
    hould
    0.62
     should
    0.60
     SHOULD
    0.57
    应该
    0.48
    不应该
    0.47
    ShouldBe
    0.45
     shouldBe
    0.42
    Act Density 0.002%

    No Known Activations