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

    Neuronpedia

    INDEX
    Explanations

    phrases related to police activity and law enforcement actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to police actions and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.01
    2:0.13
    3:0.17
    4:0.03
    5:0.37
    6:0.02
    7:0.07
    8:0.06
    9:0.02
    10:0.03
    11:0.01
    Negative Logits
    Army
    -3.61
     generals
    -3.31
     USAF
    -3.28
    Military
    -3.09
     DOD
    -3.05
     missions
    -2.97
     military
    -2.97
    Defense
    -2.95
     bureaucracy
    -2.94
     armies
    -2.94
    POSITIVE LOGITS
     rapper
    2.51
    iddler
    2.34
    susp
    2.34
     suspicious
    2.31
    arijuana
    2.31
     suspect
    2.30
     robbery
    2.28
    geist
    2.28
     disturbance
    2.26
    uana
    2.25
    Act Density 1.075%

    No Known Activations