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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and end of statement indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     \"%
    -0.55
    achim
    -0.54
     ($(
    -0.53
     (_
    -0.53
     (“
    -0.52
     "{{
    -0.52
     factory
    -0.51
    úrate
    -0.51
    (?:
    -0.51
     blo
    -0.51
    POSITIVE LOGITS
     مشين
    0.79
     وتسجيلات
    0.77
    GEBURTSDATUM
    0.77
    ViewFeatures
    0.75
    ंदीखरीदारी
    0.72
     estimés
    0.71
    脚注の使い方
    0.71
     للاسماء
    0.69
     AssemblyTitle
    0.65
    ffindor
    0.64
    Act Density 0.047%

    No Known Activations