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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence-ending structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wik
    -0.17
    ervo
    -0.15
    каÑģ
    -0.14
    eps
    -0.14
    hrad
    -0.14
    zet
    -0.13
    uitka
    -0.13
    Datas
    -0.13
    ETHOD
    -0.13
    iveau
    -0.13
    POSITIVE LOGITS
    quo
    0.16
     Sabha
    0.16
     Pradesh
    0.15
     Lumpur
    0.14
    aterno
    0.14
    ủa
    0.14
    oard
    0.13
     tion
    0.13
     Zealand
    0.13
    åĨĨ
    0.13
    Act Density 0.394%

    No Known Activations