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

    Neuronpedia

    INDEX
    Explanations

    mentions of identification (ID) cards or numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of identification (ID)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.88
    cffff
    -0.71
    bilt
    -0.69
    uckland
    -0.68
    orld
    -0.68
    Ò
    -0.68
    =-=-
    -0.67
    ategory
    -0.66
    terday
    -0.66
     Silence
    -0.65
    POSITIVE LOGITS
    iots
    1.15
    aho
    1.01
    DEN
    0.94
    entity
    0.92
    irect
    0.84
     ID
    0.84
    ENT
    0.82
    iop
    0.82
    ocument
    0.82
    LER
    0.81
    Act Density 0.011%

    No Known Activations