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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utan
    -0.14
    762
    -0.14
    anes
    -0.14
     Sham
    -0.13
     Firstly
    -0.13
    -dis
    -0.13
    ü
    -0.12
     undert
    -0.12
    imon
    -0.12
    .env
    -0.12
    POSITIVE LOGITS
    âĸį
    0.16
    richt
    0.14
    arty
    0.14
     Söz
    0.14
    /******/
    0.14
    ģm
    0.14
    quelle
    0.14
    allee
    0.14
    ģn
    0.14
    kening
    0.14
    Act Density 0.057%

    No Known Activations