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

    Neuronpedia

    INDEX
    Explanations

    references to specific nationalities and ethnic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.19
     prostitutas
    -0.17
    eson
    -0.15
    edor
    -0.15
    lying
    -0.15
    ful
    -0.14
    ship
    -0.14
    berapa
    -0.14
    344
    -0.14
    tainment
    -0.14
    POSITIVE LOGITS
    /OR
    0.20
    -American
    0.19
    -Americans
    0.17
    /left
    0.17
     who
    0.16
    imals
    0.16
    -Muslim
    0.15
    boro
    0.15
    /N
    0.15
    aurus
    0.14
    Act Density 0.101%

    No Known Activations