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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain special characters in a mathematical context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Bylo
    -0.07
    ebek
    -0.06
    ]={↵
    -0.06
    ÑĪки
    -0.06
    ennie
    -0.06
     )↵↵↵↵↵↵↵↵
    -0.06
    plits
    -0.06
    ¦y
    -0.06
     Ùħت
    -0.06
    znám
    -0.06
    POSITIVE LOGITS
    olls
    0.07
    èĮĤ
    0.07
    YLES
    0.06
    ulo
    0.06
    ionic
    0.06
    keh
    0.06
    rix
    0.06
    ación
    0.06
    ecom
    0.06
    /gin
    0.06
    Act Density 0.264%

    No Known Activations