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

    Neuronpedia

    INDEX
    Explanations

    various forms of whitespace and empty elements in the document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.17
    ſelben
    -1.06
    MLLoader
    -1.05
     Biôgrafia
    -1.05
    iſchen
    -1.02
    UrlResolution
    -1.01
    +#+
    -0.99
    ьаж
    -0.98
     autorytatywna
    -0.98
    ########.
    -0.98
    POSITIVE LOGITS
    if
    0.48
    <
    0.42
     the
    0.39
     an
    0.37
     a
    0.37
    On
    0.36
      
    0.35
        
    0.35
         
    0.35
    //
    0.35
    Act Density 0.090%

    No Known Activations