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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their context within sentences

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

    Punctuation followed by conjunctions or adverbs

    np_acts-logits-general · gemini-2.0-flash

    introduces additional clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.97
     initComponents
    -0.91
    twimg
    -0.87
    stdc
    -0.77
     doInBackground
    -0.71
     ComVisible
    -0.69
     '-':
    -0.69
    发表于
    -0.68
    Lähteet
    -0.68
     BoxDecoration
    -0.68
    POSITIVE LOGITS
    (
    0.66
     Whilst
    0.65
     However
    0.60
     whilst
    0.59
     (
    0.58
     therefor
    0.58
    Whilst
    0.57
    ,,
    0.56
     cuales
    0.53
     It
    0.52
    Act Density 0.558%

    No Known Activations