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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     valida
    -0.16
    HR
    -0.14
     addCriterion
    -0.14
    hr
    -0.13
     ack
    -0.13
    един
    -0.13
    à¸Ńà¸Ńà¸ģ
    -0.13
     ÎĵεÏī
    -0.13
     unpopular
    -0.13
     Ground
    -0.13
    POSITIVE LOGITS
    slots
    0.15
    udades
    0.15
    DATED
    0.15
    oble
    0.15
    orsi
    0.14
    quotes
    0.14
    zk
    0.14
    Quote
    0.14
    Å®
    0.14
    eriod
    0.14
    Act Density 0.032%

    No Known Activations