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

    Neuronpedia

    INDEX
    Explanations

    references to WiFi-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to WiFi connectivity and its quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abeth
    -0.77
    bred
    -0.74
    teen
    -0.69
    agall
    -0.67
    orate
    -0.67
    ean
    -0.67
    raised
    -0.66
    ums
    -0.66
    raught
    -0.66
    oral
    -0.65
    POSITIVE LOGITS
     WiFi
    1.13
     hots
    0.95
     Hots
    0.95
    Wi
    0.91
     wifi
    0.88
     Wi
    0.83
     connectivity
    0.82
    Adapter
    0.80
     networking
    0.78
     routers
    0.77
    Act Density 0.004%

    No Known Activations