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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement and police officers

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

    actions by police officers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⤹
    -0.46
    BindView
    -0.46
    QMetaType
    -0.42
    ]")]
    -0.42
    satisfaction
    -0.41
    isseaux
    -0.41
     forfait
    -0.41
    Bissau
    -0.41
     bisher
    -0.40
    XmlSchema
    -0.40
    POSITIVE LOGITS
     policeman
    1.15
    Officer
    1.03
     officer
    0.96
     policemen
    0.94
     OFFICER
    0.91
     Officer
    0.91
    officer
    0.90
     police
    0.87
    police
    0.84
     Police
    0.82
    Act Density 0.010%

    No Known Activations