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

    Neuronpedia

    INDEX
    Explanations

    terms related to data exposure and security vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tube
    -0.15
    .metro
    -0.14
     manoe
    -0.14
    ilate
    -0.14
    coop
    -0.14
    adt
    -0.13
     colabor
    -0.13
    mpp
    -0.13
    edata
    -0.13
     coop
    -0.13
    POSITIVE LOGITS
     scan
    0.28
     scanned
    0.25
     scans
    0.24
     scanning
    0.23
     exposures
    0.23
     discovery
    0.23
     scanner
    0.23
     Scan
    0.23
     enumeration
    0.22
     exposure
    0.21
    Act Density 0.013%

    No Known Activations