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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks and structure in the text, indicating the presence of quoted or referenced speech

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quoted ellipses and parentheticals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.97
     المعيارى
    -0.96
     فريبيس
    -0.95
    Portale
    -0.94
     nahilalakip
    -0.93
    évaluateur
    -0.89
    AsUp
    -0.88
     ويكيميديا
    -0.88
     GIPHY
    -0.85
    SharedDtor
    -0.85
    POSITIVE LOGITS
    …
    1.32
    ...
    1.31
     ...
    1.27
     …
    1.22
    ....
    0.99
    ….
    0.97
     […]
    0.91
     [...]
    0.89
    ..
    0.88
     “…
    0.85
    Act Density 0.247%

    No Known Activations