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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security and the word "secure"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.78
    udi
    -0.77
    ãĥ¼ãĤ¯
    -0.71
    swick
    -0.70
    govtrack
    -0.69
    bender
    -0.69
    kens
    -0.69
    gom
    -0.67
    ague
    -0.66
    asin
    -0.66
    POSITIVE LOGITS
     anonymity
    0.92
     against
    0.85
     confidentiality
    0.84
     passwords
    0.84
     access
    0.83
     perimeter
    0.83
     deposit
    0.81
     Deposit
    0.81
     footing
    0.80
     enclave
    0.79
    Act Density 0.084%

    No Known Activations