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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "A" preceded by a space or punctuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'A' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.68
     optics
    -0.65
    assetsadobe
    -0.64
     intended
    -0.62
     enclosed
    -0.61
     accuracy
    -0.59
     ordering
    -0.58
     intuitive
    -0.58
     order
    -0.57
     noses
    -0.56
    POSITIVE LOGITS
    perture
    1.31
    ussie
    1.28
    cknowled
    1.14
    vant
    1.11
    verages
    1.09
    ryan
    1.08
    UG
    1.08
    lyss
    1.07
    uctions
    1.04
    VID
    1.04
    Act Density 0.051%

    No Known Activations