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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hipster
    -0.17
    :↵↵
    -0.15
     ↵↵
    -0.14
    uder
    -0.14
     ↵
    -0.14
     Rank
    -0.14
    acey
    -0.14
    inary
    -0.13
     atmosphere
    -0.13
    abl
    -0.13
    POSITIVE LOGITS
    bern
    0.17
    chwitz
    0.16
    ystack
    0.15
    ầy
    0.15
    lean
    0.15
     lesbi
    0.15
    onces
    0.14
    /photo
    0.14
    urdy
    0.14
    ioned
    0.14
    Act Density 0.103%

    No Known Activations