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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of police officers with their titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police officers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tea
    -0.93
    dos
    -0.85
    tera
    -0.84
    creen
    -0.82
    ites
    -0.81
    kered
    -0.80
    iceps
    -0.78
    ankind
    -0.78
    hend
    -0.77
    ilaterally
    -0.77
    POSITIVE LOGITS
     officer
    0.91
     corps
    0.88
     examiner
    0.86
     homicide
    0.80
    geant
    0.79
     officers
    0.78
     informant
    0.78
     stationed
    0.77
     Officer
    0.76
    utenant
    0.75
    Act Density 0.052%

    No Known Activations