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

    Neuronpedia

    INDEX
    Explanations

    The neuron is looking for references to government offices, particularly the "Home Office" in UK contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to government or official organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Washington
    -0.84
     Hawai
    -0.83
     UW
    -0.80
     favorable
    -0.78
     unfavorable
    -0.77
    Seattle
    -0.76
    plet
    -0.74
     labeling
    -0.74
    Ô
    -0.72
     Texans
    -0.72
    POSITIVE LOGITS
    £
    1.52
     £
    1.38
     Scotland
    1.27
    Scotland
    1.21
    Britain
    1.19
    abulary
    1.11
     Britain
    1.09
    BBC
    1.09
     England
    1.07
    CHQ
    1.04
    Act Density 0.343%

    No Known Activations