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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law enforcement or police activities

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement or police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.89
    igible
    -0.84
    yip
    -0.81
    bp
    -0.76
    amic
    -0.76
    ranged
    -0.74
    thal
    -0.73
    ceivable
    -0.72
    eem
    -0.71
    wered
    -0.70
    POSITIVE LOGITS
     departments
    1.01
     officers
    1.00
     officer
    0.92
     brutality
    0.87
     blot
    0.86
     commissioner
    0.84
     Constable
    0.82
     academy
    0.82
     chiefs
    0.80
     enforcement
    0.80
    Act Density 0.065%

    No Known Activations