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

    Neuronpedia

    INDEX
    Explanations

    references to police-related activities or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aight
    -0.18
    adr
    -0.17
     nackte
    -0.16
    Margins
    -0.16
     army
    -0.15
     ном
    -0.15
    pery
    -0.14
    bane
    -0.14
    webdriver
    -0.14
    /key
    -0.14
    POSITIVE LOGITS
     duty
    0.24
     badge
    0.23
     rookies
    0.22
     colleague
    0.21
     colleagues
    0.21
     uniform
    0.21
     duties
    0.20
     Duty
    0.20
     patrol
    0.20
     rookie
    0.19
    Act Density 0.203%

    No Known Activations