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

    Neuronpedia

    INDEX
    Explanations

    concerns about online privacy and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ër
    -0.15
     fathers
    -0.15
    aco
    -0.15
    udents
    -0.14
    uml
    -0.14
     समर
    -0.14
     corner
    -0.14
    ë³Ħ
    -0.14
    EventType
    -0.13
    Opaque
    -0.13
    POSITIVE LOGITS
     Vulner
    0.29
     vulnerable
    0.29
     vulnerability
    0.27
     vulnerabilities
    0.25
     vulner
    0.25
     unprotected
    0.21
     Achilles
    0.20
     exposed
    0.20
     Exposure
    0.18
     suscept
    0.18
    Act Density 0.090%

    No Known Activations