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

    Neuronpedia

    INDEX
    Explanations

    references to secrecy and classified information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    моÑĢ
    -0.16
     tray
    -0.15
     Tray
    -0.15
     Suspension
    -0.14
     dest
    -0.14
    PropTypes
    -0.14
    оÑĢÑĤ
    -0.13
    623
    -0.13
     Moran
    -0.13
     suspended
    -0.13
    POSITIVE LOGITS
     until
    0.21
     privacy
    0.19
     secrecy
    0.19
    until
    0.18
     mystery
    0.16
     confidentiality
    0.16
     closed
    0.16
    lest
    0.16
    privacy
    0.16
    Privacy
    0.16
    Act Density 0.147%

    No Known Activations