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

    Neuronpedia

    INDEX
    Explanations

    references to HTTP-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to HTTP and web protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cum
    -0.80
    bryce
    -0.78
    arist
    -0.77
    ynski
    -0.76
    ________________
    -0.75
    bourg
    -0.74
    vette
    -0.73
    lie
    -0.73
    ggies
    -0.72
    hani
    -0.72
    POSITIVE LOGITS
    ://
    1.07
     HTTP
    1.04
     connection
    0.96
     connections
    0.94
    HTTP
    0.92
     traffic
    0.91
     headers
    0.89
     connectivity
    0.89
     UDP
    0.87
     Connection
    0.87
    Act Density 0.054%

    No Known Activations