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

    Neuronpedia

    INDEX
    Explanations

    references to racism and its social implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Christmas
    -0.15
    å¾³
    -0.15
     christmas
    -0.15
    otre
    -0.14
    osti
    -0.14
    bakan
    -0.14
     ushort
    -0.14
    implify
    -0.14
    ilde
    -0.14
    rove
    -0.14
    POSITIVE LOGITS
     police
    0.19
     Floyd
    0.18
     racial
    0.18
     racism
    0.18
     Black
    0.17
     Police
    0.17
     race
    0.16
    unity
    0.16
     policing
    0.15
     white
    0.15
    Act Density 0.079%

    No Known Activations