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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers, such as keys, within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to keys associated with security or encryption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliation
    -0.76
    govtrack
    -0.73
    shoot
    -0.72
    isode
    -0.72
    regnancy
    -0.69
    han
    -0.69
    ultural
    -0.66
    ascist
    -0.66
    hu
    -0.65
    elle
    -0.65
    POSITIVE LOGITS
     keys
    3.88
     Keys
    2.66
    keys
    2.47
    Keys
    2.20
     key
    1.92
     keyboards
    1.65
     KEY
    1.59
    Key
    1.59
    key
    1.58
     Key
    1.58
    Act Density 0.012%

    No Known Activations