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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

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

    Commas followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    ending clauses with commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.58
     voda
    -0.55
    Taken
    -0.52
    ∛
    -0.52
     setw
    -0.52
    󠁢
    -0.51
    ΩΝ
    -0.50
    fycat
    -0.49
    nehm
    -0.49
    といって
    -0.49
    POSITIVE LOGITS
     had
    0.83
     was
    0.82
     has
    0.82
     will
    0.78
     is
    0.76
     tartalomajánló
    0.70
     would
    0.69
    ViewImports
    0.68
     could
    0.67
    DoubleQuotes
    0.66
    Act Density 0.211%

    No Known Activations