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

    Neuronpedia

    INDEX
    Explanations

    elements related to security and privacy concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æģµ
    -0.16
     Ïį
    -0.14
    ãĥĥãĤ¯ãĤ¹
    -0.14
    noch
    -0.14
    strom
    -0.13
    chez
    -0.13
    ÑĩаÑģ
    -0.13
    lsa
    -0.13
    uslim
    -0.13
     gaussian
    -0.13
    POSITIVE LOGITS
     COP
    0.34
     FTC
    0.30
     kids
    0.25
     disclosures
    0.25
     children
    0.24
     Kids
    0.24
     kid
    0.24
     CCP
    0.24
     privacy
    0.23
     consumer
    0.23
    Act Density 0.005%

    No Known Activations