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

    Neuronpedia

    INDEX
    Explanations

    instances of mentions or discussions of the use of force, particularly in law enforcement contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the use of force, particularly in law enforcement and military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rib
    -0.73
     Lime
    -0.69
     Coil
    -0.66
    akis
    -0.63
    unct
    -0.63
    ixture
    -0.63
    uez
    -0.61
     Lov
    -0.61
     Adin
    -0.61
    seq
    -0.61
    POSITIVE LOGITS
     inappropriately
    0.98
     sparing
    0.96
     responsibly
    0.95
     wisely
    0.95
     efficiently
    0.93
     GOODMAN
    0.92
     unlawfully
    0.91
     offensively
    0.85
     defensively
    0.83
     indiscrim
    0.81
    Act Density 0.162%

    No Known Activations