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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numeric values within a code or data structure context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    token followed by digit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.69
    UnitTesting
    -0.66
    addPreferredGap
    -0.66
     للمعارف
    -0.65
     وتسجيلات
    -0.65
    GEBURTSDATUM
    -0.63
    WriteLiteral
    -0.61
    msgTypes
    -0.60
    InjectAttribute
    -0.59
    ագրություններ
    -0.59
    POSITIVE LOGITS
    Allgemeine
    0.39
    =()=>{
    0.34
    }{(
    0.32
    ​
    0.32
     []:
    0.31
     Bohn
    0.31
    ',(
    0.30
    <
    0.30
     Bakker
    0.30
     ();
    0.30
    Act Density 0.048%

    No Known Activations