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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific letter combinations or patterns, particularly those starting with "th," "oth," or containing repeated sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ez
    -0.22
    er
    -0.19
    ER
    -0.19
    ease
    -0.18
    ech
    -0.18
    ee
    -0.17
    eh
    -0.17
    tero
    -0.16
    ei
    -0.16
    wner
    -0.16
    POSITIVE LOGITS
    ttp
    0.30
    entication
    0.27
    ematics
    0.24
    ompson
    0.23
    edral
    0.23
    aniel
    0.23
    ousand
    0.22
    odoxy
    0.22
    ousands
    0.22
    à¥įà¤ł
    0.22
    Act Density 0.089%

    No Known Activations