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

    Neuronpedia

    INDEX
    Explanations

    technical language and programming-related terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     mas
    -0.47
     mean
    -0.47
    nat
    -0.47
     '#'
    -0.46
    gnu
    -0.44
    digos
    -0.44
    nash
    -0.44
    ian
    -0.43
    INC
    -0.43
    StatusCodes
    -0.43
    POSITIVE LOGITS
    تقاوى
    0.76
    IVEREF
    0.76
     nahilalakip
    0.74
     Савезне
    0.71
    GEBURTSDATUM
    0.66
    出版年
    0.65
     Италијани
    0.65
     */
    0.65
     ujednoznacz
    0.63
    pperware
    0.61
    Act Density 0.231%

    No Known Activations