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

    Neuronpedia

    INDEX
    Explanations

    patterns and relationships among mathematical symbols and variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     puis
    -0.43
     usted
    -0.43
    read
    -0.43
    ngua
    -0.41
     while
    -0.40
     use
    -0.40
    ◀
    -0.40
     
    -0.39
    Output
    -0.39
     if
    -0.38
    POSITIVE LOGITS
     Мексичка
    0.93
    ArgsConstructor
    0.87
    fjspx
    0.86
     Roskov
    0.77
    الدراسه
    0.75
    +#+#
    0.72
     الحره
    0.72
     становника
    0.71
    RegistryLite
    0.69
     Савезне
    0.69
    Act Density 0.035%

    No Known Activations