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

    Neuronpedia

    INDEX
    Explanations

    patterns related to case sensitivity in character representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.69
     विश्वसनीयता
    -0.60
    Джерело
    -0.56
    inquirer
    -0.51
     ujednoznacz
    -0.51
    FieldDescriptor
    -0.50
    cloudfront
    -0.50
     autorytatywna
    -0.50
    mitos
    -0.48
    raquo
    -0.48
    POSITIVE LOGITS
    ToUpper
    0.91
     alphabet
    0.86
    uppercase
    0.82
     letters
    0.82
    capitalize
    0.78
    toupper
    0.77
     alphabets
    0.76
     Alphabet
    0.75
    toUpperCase
    0.75
    alphabet
    0.75
    Act Density 0.303%

    No Known Activations