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

    Neuronpedia

    INDEX
    Explanations

    references to police officers and their interactions or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quential
    -0.18
    anja
    -0.17
    agra
    -0.15
    íģ¼
    -0.15
    vla
    -0.14
    еÑĢин
    -0.14
    è¿°
    -0.14
    lá
    -0.14
    виÑī
    -0.14
    opal
    -0.14
    POSITIVE LOGITS
    ono
    0.15
    471
    0.14
    hood
    0.14
    true
    0.14
    ental
    0.14
    768
    0.14
    sw
    0.13
     Ot
    0.13
     TRUE
    0.13
    921
    0.13
    Act Density 0.039%

    No Known Activations