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

    Neuronpedia

    INDEX
    Explanations

    punctuation and citation references in texts

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

    Punctuation at the end of sentences

    np_acts-logits-general · gemini-2.0-flash

    citations and bibliographical references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -1.00
     ویکی‌پدیا
    -0.92
     незавершена
    -0.82
     كومونز
    -0.79
    NameInMap
    -0.77
    IsMutable
    -0.77
    nodoc
    -0.76
    Datuak
    -0.75
    +#+
    -0.73
    </thead>
    -0.73
    POSITIVE LOGITS
    ↵
    0.53
    <eos>
    0.52
    ↵↵
    0.49
    ↵↵↵↵↵
    0.46
    ↵↵↵
    0.44
     contient
    0.44
     Fehler
    0.43
     noastre
    0.42
    採
    0.42
     meglio
    0.42
    Act Density 0.055%

    No Known Activations