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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or likelihood

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

    Follows a modal verb ("would," "should," "could," "might," "must")

    np_acts-logits-general · gemini-2.0-flash

    modal verb followed by have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.05
     cherchés
    -1.04
    TypedDataSet
    -1.00
    IntoConstraints
    -0.94
    rungsseite
    -0.83
    GEBURTSDATUM
    -0.77
    bewerken
    -0.76
     Wiktionnaire
    -0.73
    QMetaType
    -0.71
     kaarangay
    -0.71
    POSITIVE LOGITS
     have
    1.45
     telah
    1.24
     has
    1.23
     đã
    1.16
     geweest
    1.08
    Has
    1.03
     gewesen
    1.02
     had
    1.01
     hadn
    1.00
    Have
    0.99
    Act Density 0.422%

    No Known Activations