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

    Neuronpedia

    INDEX
    Explanations

    keywords or references related to identification documents

    oai_token-act-pair · gpt-3.5-turbo

    references to identification documents or IDs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.87
    orld
    -0.84
    cffffcc
    -0.76
    xual
    -0.76
    terday
    -0.75
    scill
    -0.72
     Sounds
    -0.68
    bilt
    -0.66
    ategory
    -0.65
    cffff
    -0.65
    POSITIVE LOGITS
    iots
    1.06
    irect
    1.01
    DEN
    0.98
     ID
    0.94
    entity
    0.89
    ividual
    0.89
    aho
    0.88
    ouble
    0.86
    ID
    0.86
     IDs
    0.84
    Act Density 0.006%

    No Known Activations