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

    Neuronpedia

    INDEX
    Explanations

    the letter "K" followed by a combination of other characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'K' followed by a number, often indicating specific characters or items in a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.76
    terday
    -0.73
     Yor
    -0.61
     Celest
    -0.61
     ascending
    -0.60
    ãĥ¼ãĥĨãĤ£
    -0.60
     letting
    -0.60
     commons
    -0.59
     wip
    -0.59
     medieval
    -0.59
    POSITIVE LOGITS
    EEP
    1.17
    rieg
    1.17
    ittens
    1.15
    udos
    1.14
    essel
    1.14
    aspers
    1.12
    ratom
    1.12
    ettle
    1.11
    nee
    1.10
    oop
    1.08
    Act Density 0.037%

    No Known Activations