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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to the term "Kiwi"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "iw" and similar variations, potentially related to a specific topic or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     succeeding
    -0.71
    inates
    -0.70
    âĸ¬âĸ¬
    -0.70
    âĸ¬
    -0.68
     penetrating
    -0.67
    inately
    -0.64
     anat
    -0.63
     ancest
    -0.61
    ++++++++++++++++
    -0.60
     fracturing
    -0.60
    POSITIVE LOGITS
    atts
    1.15
    iw
    1.06
    ombo
    1.03
    ield
    1.03
    esley
    1.01
    atcher
    1.01
    orthy
    0.99
    edge
    0.99
    ugi
    0.97
    esome
    0.97
    Act Density 0.012%

    No Known Activations