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

    Neuronpedia

    INDEX
    Explanations

    incidents involving police interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourg
    -0.15
     wor
    -0.15
     oversight
    -0.14
    igated
    -0.14
     æ®
    -0.14
    omi
    -0.14
    ırak
    -0.14
    æ¶
    -0.13
     absor
    -0.13
    cie
    -0.13
    POSITIVE LOGITS
     arrest
    0.20
     police
    0.20
    ách
    0.18
    Police
    0.18
     Police
    0.18
    æ³ķ
    0.17
     Arrest
    0.17
     profiling
    0.16
     arrests
    0.15
     cops
    0.15
    Act Density 0.122%

    No Known Activations