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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas, in the text

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

    Commas followed by conjunctions or prepositions

    np_acts-logits-general · gemini-2.0-flash

    comma then conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.91
     odkazy
    -0.86
    <bos>
    -0.80
    tvguidetime
    -0.79
    EndGlobalSection
    -0.79
    bootstrapcdn
    -0.79
    StoryboardSegue
    -0.77
    Jeografia
    -0.76
    oa̍t
    -0.76
     chi̍t
    -0.74
    POSITIVE LOGITS
    .
    1.42
    ).
    0.91
    .”
    0.88
    .\\
    0.88
    ”.
    0.83
    ".
    0.83
    ."
    0.82
    %.
    0.81
    。
    0.81
    ↵↵
    0.80
    Act Density 0.815%

    No Known Activations