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

    Neuronpedia

    INDEX
    Explanations

    the frequency of pronouns in various contexts

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

    Contractions of "I would" or "I had"

    np_acts-logits-general · gemini-2.0-flash

    "I'd" contraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.80
     <=",
    -0.72
    RenderAtEndOf
    -0.69
    minton
    -0.68
     Wikimedijinoj
    -0.66
     Roskov
    -0.66
    CodedInputStream
    -0.65
    Personensuche
    -0.64
     AspNetCore
    -0.61
    Begriffsklä
    -0.59
    POSITIVE LOGITS
    d
    1.21
     d
    1.03
     Id
    0.74
    Id
    0.69
    ’
    0.69
     id
    0.60
    д
    0.58
    id
    0.56
    D
    0.54
    𝗱
    0.53
    Act Density 0.240%

    No Known Activations