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

    Neuronpedia

    INDEX
    Explanations

    statements related to technical protocols

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific protocols related to technology or computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.77
    adows
    -0.74
    inning
    -0.69
    inese
    -0.69
    kus
    -0.67
    reens
    -0.67
    some
    -0.67
    minster
    -0.66
    inez
    -0.66
    ahar
    -0.65
    POSITIVE LOGITS
     protocols
    1.10
    ocol
    1.05
     protocol
    1.05
    eers
    1.03
     Protocol
    0.87
    eer
    0.87
     droid
    0.78
    ĨĴ
    0.77
    urally
    0.76
     handshake
    0.75
    Act Density 0.018%

    No Known Activations