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

    Neuronpedia

    INDEX
    Explanations

    tokens that reference a self-referential context or state

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

    pro se or per se

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.61
     tartalomajánló
    -0.54
    uxxxx
    -0.48
     المعيارى
    -0.46
    UnsafeEnabled
    -0.45
     handleMessage
    -0.44
     estekak
    -0.44
    IMPORTED
    -0.44
     дописавши
    -0.44
    parsedMessage
    -0.44
    POSITIVE LOGITS
    ſelf
    0.61
     kasarigan
    0.59
     fubject
    0.56
     smtplib
    0.54
     neceff
    0.52
     ſtate
    0.50
     houſe
    0.50
     ſch
    0.49
    stateMutability
    0.49
     ſta
    0.49
    Act Density 0.005%

    No Known Activations