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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases that challenge assertions or beliefs

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

    "Did" or "did" at the beginning of clauses/sentences

    np_acts-logits-general · gemini-2.0-flash

    detecting did and did not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    currently
    -0.49
     Houſe
    -0.47
    rungsseite
    -0.47
    IntoConstraints
    -0.47
     currently
    -0.46
     now
    -0.45
     désormais
    -0.45
    ContentValues
    -0.45
     houſe
    -0.45
     actuellement
    -0.44
    POSITIVE LOGITS
     Did
    0.68
    did
    0.66
    Did
    0.64
    DID
    0.59
     did
    0.59
     previously
    0.58
     DID
    0.56
     recently
    0.55
     originally
    0.54
    recently
    0.53
    Act Density 0.086%

    No Known Activations