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

    Neuronpedia

    INDEX
    Explanations

    keywords related to encryption and security protocols

    oai_token-act-pair · gpt-3.5-turbo

    references to public keys and associated data in the context of technology or security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.87
     Ic
    -0.77
    joined
    -0.69
    bridge
    -0.65
    cles
    -0.64
    izen
    -0.64
    appropriately
    -0.61
     Bie
    -0.60
    andowski
    -0.58
     thirds
    -0.58
    POSITIVE LOGITS
    asus
    1.01
    raph
    1.00
    iants
    0.97
    raphic
    0.95
    omez
    0.91
    regor
    0.88
    TA
    0.86
    PI
    0.85
    HHHH
    0.84
    allery
    0.84
    Act Density 0.035%

    No Known Activations