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

    Neuronpedia

    INDEX
    Explanations

    phrases and references to responsibility and accountability in legal contexts

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

    Follows pronouns or nouns, and precedes "did"

    np_acts-logits-general · gemini-2.0-flash

    past tense auxiliaries and modals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.62
     متعلقه
    -0.61
    #+#
    -0.61
    RectangleBorder
    -0.59
    TintMode
    -0.57
    mog
    -0.57
    SupportActionBar
    -0.54
    Portály
    -0.54
    jsxFileName
    -0.54
    Abitanti
    -0.53
    POSITIVE LOGITS
     did
    2.07
    did
    1.73
     Did
    1.66
    Did
    1.62
     didn
    1.56
    didn
    1.35
     DID
    1.31
     didnt
    1.29
     Didn
    1.25
    DID
    1.25
    Act Density 0.287%

    No Known Activations