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

    Neuronpedia

    INDEX
    Explanations

    words related to security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security and encryption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.75
    è¦ļéĨĴ
    -0.74
    bender
    -0.72
    ¢
    -0.69
    swick
    -0.69
    Kay
    -0.67
    oths
    -0.65
    VL
    -0.65
    ptions
    -0.64
    hur
    -0.64
    POSITIVE LOGITS
     handshake
    0.84
     enclave
    0.84
     cryptographic
    0.79
    heed
    0.79
     perimeter
    0.78
    ness
    0.75
     Secure
    0.73
    ment
    0.72
     adolesc
    0.72
    Random
    0.70
    Act Density 0.031%

    No Known Activations