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

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ril
    -0.77
    abeth
    -0.76
    orian
    -0.75
    amental
    -0.74
    bred
    -0.73
    ean
    -0.72
    othe
    -0.71
    chin
    -0.70
    nings
    -0.70
    aryl
    -0.70
    POSITIVE LOGITS
     Hots
    0.96
     WiFi
    0.95
     hots
    0.92
    Wi
    0.83
     Connection
    0.81
    Roaming
    0.79
    LED
    0.77
     wifi
    0.76
    Adapter
    0.75
     connectivity
    0.73
    Act Density 0.010%

    No Known Activations