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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement and officers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schmel
    -0.70
    ————————————————
    -0.70
    <strong>
    -0.67
    gunaan
    -0.66
     lilla
    -0.65
    ——–
    -0.65
    Spar
    -0.64
     Sanford
    -0.63
    _
    -0.63
    vec
    -0.62
    POSITIVE LOGITS
     officers
    1.36
     Officers
    1.36
     OFFICER
    1.34
    officer
    1.31
    officers
    1.30
    Officers
    1.28
     OFFICERS
    1.28
     Officer
    1.27
    Officer
    1.19
     officer
    1.18
    Act Density 0.074%

    No Known Activations