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

    Neuronpedia

    INDEX
    Explanations

    instances of past actions or states described through the word "was."

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

    past tense questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fillType
    -0.53
    IntoConstraints
    -0.52
     currently
    -0.42
     ویکی‌پدیای
    -0.42
    blockList
    -0.41
    Currently
    -0.41
     fixtures
    -0.40
    ImageContext
    -0.40
    currently
    -0.40
    RenderAtEndOf
    -0.40
    POSITIVE LOGITS
    Did
    0.54
     Did
    0.53
     yesterday
    0.49
    did
    0.47
     DID
    0.46
    Cyfarwyddwr
    0.46
    Yesterday
    0.45
     Yesterday
    0.45
     passado
    0.45
     vergangenen
    0.45
    Act Density 0.238%

    No Known Activations