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

    Neuronpedia

    INDEX
    Explanations

    mentions of law enforcement or police-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osi
    -0.88
    xual
    -0.88
    yip
    -0.82
    culosis
    -0.79
    thal
    -0.78
    owship
    -0.76
    ocene
    -0.74
    pread
    -0.71
    adium
    -0.70
    vironment
    -0.70
    POSITIVE LOGITS
     officers
    1.18
     informant
    0.99
     departments
    0.97
     investigators
    0.97
     officer
    0.92
     Officers
    0.92
     informants
    0.90
     authorities
    0.87
     brutality
    0.87
     academy
    0.86
    Act Density 0.044%

    No Known Activations