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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods, question marks, and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _SUFFIX
    -0.15
    remium
    -0.15
    oro
    -0.13
    خصÙĪص
    -0.13
     Crafts
    -0.12
    urtle
    -0.12
     Setter
    -0.12
    co
    -0.12
    .oauth
    -0.12
    ayne
    -0.12
    POSITIVE LOGITS
    rosso
    0.17
    ories
    0.15
    bservice
    0.15
    jedn
    0.14
    rame
    0.14
    ìĿ´ìĸ´
    0.14
    altung
    0.14
    hole
    0.14
    rosse
    0.14
    ITH
    0.13
    Act Density 0.256%

    No Known Activations