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

    Neuronpedia

    INDEX
    Explanations

    words related to police work and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to policing and law enforcement practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quart
    -0.89
    psons
    -0.79
    rator
    -0.77
    hus
    -0.76
    isy
    -0.75
    yip
    -0.74
    wives
    -0.74
    abee
    -0.72
    rin
    -0.72
    hof
    -0.72
    POSITIVE LOGITS
     policing
    0.88
     polic
    0.81
     crackdown
    0.72
     enforcement
    0.70
     discretionary
    0.70
     spree
    0.67
     brutality
    0.66
     Notting
    0.65
     precincts
    0.65
     narcotics
    0.65
    Act Density 0.027%

    No Known Activations