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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or sequences of letters in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ký
    -0.17
    eve
    -0.17
    acent
    -0.15
    adera
    -0.15
    itous
    -0.14
    ös
    -0.14
    proto
    -0.14
    avor
    -0.14
    amd
    -0.14
    adero
    -0.14
    POSITIVE LOGITS
    lings
    0.20
    iness
    0.19
    ings
    0.19
    side
    0.18
    ãĥªãĥ³ãĤ°
    0.17
    month
    0.17
    urement
    0.17
    water
    0.17
    sville
    0.16
    ONS
    0.16
    Act Density 0.053%

    No Known Activations