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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical protocols

    oai_token-act-pair · gpt-3.5-turbo

    references to various protocols and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adows
    -0.79
    reens
    -0.70
    oln
    -0.69
    inese
    -0.68
    some
    -0.67
    hiro
    -0.65
    artz
    -0.65
    itate
    -0.65
    alsh
    -0.64
    inez
    -0.64
    POSITIVE LOGITS
     protocol
    1.30
     protocols
    1.24
     Protocol
    1.09
    ocol
    1.02
    eers
    0.94
    DragonMagazine
    0.90
     handshake
    0.89
    ĨĴ
    0.86
     etiquette
    0.78
     tcp
    0.73
    Act Density 0.010%

    No Known Activations