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

    Neuronpedia

    INDEX
    Explanations

    instances of specific letters and their frequencies in words, particularly focusing on the letters "t", "e", "b", "n", "f", and "r"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actly
    -0.15
    uably
    -0.14
    oubtedly
    -0.13
    zelf
    -0.13
    ensibly
    -0.13
    neath
    -0.13
    iously
    -0.13
    ulously
    -0.12
    ¢
    -0.12
    irtual
    -0.12
    POSITIVE LOGITS
    aviest
    0.21
    quirer
    0.19
    inator
    0.17
    osphere
    0.17
    iverse
    0.17
    liest
    0.17
     proverb
    0.17
    .scalablytyped
    0.16
    ighest
    0.16
    ghest
    0.15
    Act Density 0.405%

    No Known Activations