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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archy
    -0.14
     æļ
    -0.14
    vise
    -0.14
     bán
    -0.14
    º
    -0.13
    orp
    -0.13
    Biz
    -0.13
     гÑĢе
    -0.13
     κι
    -0.13
    _UC
    -0.13
    POSITIVE LOGITS
     tens
    0.16
    iego
    0.15
    rin
    0.15
    ocale
    0.15
    iegel
    0.14
     Mr
    0.14
    iap
    0.14
    inalg
    0.14
     Parcel
    0.14
    itten
    0.13
    Act Density 0.000%

    No Known Activations