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

    Neuronpedia

    INDEX
    Explanations

    specific identification information or documents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ID" and related phrases indicating forms of identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.77
    bilt
    -0.76
    theless
    -0.75
    uckland
    -0.68
    Ò
    -0.68
    iful
    -0.68
    uten
    -0.67
    xual
    -0.67
    cffff
    -0.66
    orld
    -0.66
    POSITIVE LOGITS
    iots
    1.09
    aho
    1.03
    DEN
    0.99
    entity
    0.99
    ENT
    0.88
    irect
    0.88
    ictionary
    0.81
    ocument
    0.81
    LER
    0.80
     ID
    0.80
    Act Density 0.014%

    No Known Activations