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

    Neuronpedia

    INDEX
    Explanations

    the structure and formatting of mathematical expressions and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     censi
    -0.74
    ers
    -0.74
    ص
    -0.72
    т
    -0.71
    Ester
    -0.71
     مص
    -0.70
    oye
    -0.70
     Schuster
    -0.69
    ي
    -0.69
    er
    -0.68
    POSITIVE LOGITS
    )\
    1.28
     {}\
    1.23
    __':
    1.19
    ()\
    1.19
    }\
    1.17
    __":
    1.15
    {}\
    1.09
    '\
    1.08
     }}\
    1.06
    ']))
    1.06
    Act Density 0.410%

    No Known Activations