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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement and police activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.90
    yip
    -0.88
    igible
    -0.82
    uces
    -0.78
    nces
    -0.76
    bp
    -0.75
    ranged
    -0.75
    loe
    -0.73
     Daylight
    -0.71
    vironment
    -0.71
    POSITIVE LOGITS
     departments
    1.08
     officers
    1.07
     officer
    1.00
     academy
    0.99
     acad
    0.95
     brutality
    0.93
     Officers
    0.93
     commissioner
    0.90
     chiefs
    0.87
     department
    0.85
    Act Density 0.056%

    No Known Activations