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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izar
    -0.15
     fon
    -0.15
     pyramid
    -0.15
    u
    -0.15
    afi
    -0.14
    quier
    -0.14
    x
    -0.14
     ref
    -0.14
    ass
    -0.14
    int
    -0.14
    POSITIVE LOGITS
    chet
    0.17
    ritten
    0.16
    edin
    0.15
    escaping
    0.15
    gran
    0.15
    asca
    0.15
    OLUMN
    0.14
    dust
    0.14
    08
    0.14
    ewire
    0.14
    Act Density 0.013%

    No Known Activations