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

    Neuronpedia

    INDEX
    Explanations

    terms related to classified information or documents

    oai_token-act-pair · gpt-3.5-turbo

    references to classified information and related materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.80
    Kay
    -0.72
    soDeliveryDate
    -0.71
    LI
    -0.70
    oller
    -0.69
    à
    -0.69
    Philipp
    -0.66
    DAY
    -0.66
    Marco
    -0.63
     Beard
    -0.63
    POSITIVE LOGITS
     briefings
    1.20
     documents
    1.01
    oslov
    0.93
     markings
    0.90
     material
    0.89
     information
    0.89
     papers
    0.86
    classified
    0.86
     classified
    0.81
     intel
    0.81
    Act Density 0.043%

    No Known Activations