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

    Neuronpedia

    INDEX
    Explanations

    terms related to data security and encryption

    oai_token-act-pair · gpt-3.5-turbo

    references to encryption and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pal
    -0.72
    ogie
    -0.70
    typ
    -0.69
     Park
    -0.68
     Pit
    -0.67
     GI
    -0.67
     Mus
    -0.66
     Urban
    -0.65
     Willie
    -0.64
     Louis
    -0.63
    POSITIVE LOGITS
     encryption
    3.54
     encrypted
    2.63
     encrypt
    2.51
     cryptography
    2.38
     cryptographic
    2.07
    ryption
    2.04
     decrypt
    1.90
     cipher
    1.85
    encrypted
    1.64
     passwords
    1.62
    Act Density 0.015%

    No Known Activations