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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hibit
    -0.17
    xac
    -0.15
    ingly
    -0.14
    imax
    -0.14
    евÑĸ
    -0.13
    antage
    -0.13
    >,</
    -0.13
    ("")]↵
    -0.13
    hic
    -0.13
    ungen
    -0.13
    POSITIVE LOGITS
     outside
    0.30
     Outside
    0.30
    Outside
    0.28
     aside
    0.28
     Aside
    0.25
    outside
    0.25
     apart
    0.24
     hobbies
    0.24
     ngoÃłi
    0.23
    Favorite
    0.23
    Act Density 0.111%

    No Known Activations