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

    Neuronpedia

    INDEX
    Explanations

    references to privacy policies and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     capit
    -0.15
    ziaÅĤ
    -0.15
    <<(
    -0.15
    piel
    -0.14
    -invalid
    -0.14
    quo
    -0.14
    pNet
    -0.14
    izzo
    -0.14
    assic
    -0.14
    reader
    -0.14
    POSITIVE LOGITS
     Privacy
    0.22
     privacy
    0.21
    Privacy
    0.19
    Sensitive
    0.18
     dealing
    0.18
    privacy
    0.17
     personal
    0.17
    _sensitive
    0.17
     Personal
    0.17
    collection
    0.17
    Act Density 0.005%

    No Known Activations