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

    Neuronpedia

    INDEX
    Explanations

    highly frequent or repetitive numerical patterns or sequences

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

    spoken dialogue markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.96
    parsedMessage
    -0.87
     ब्रेकडाउन
    -0.83
    Jereo
    -0.77
     ujednoznacz
    -0.77
    ंदीखरीदारी
    -0.76
     <>",
    -0.75
     defaultstate
    -0.73
     >=",
    -0.73
    GTCX
    -0.72
    POSITIVE LOGITS
     “
    0.41
    The
    0.39
    “
    0.38
    '
    0.36
     the
    0.35
     "
    0.35
     Abonnez
    0.35
     '
    0.34
     a
    0.33
     The
    0.33
    Act Density 0.032%

    No Known Activations