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

    Neuronpedia

    INDEX
    Explanations

    references to diversity and inclusivity across various backgrounds and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icator
    -0.17
    emode
    -0.15
    isque
    -0.15
    eral
    -0.15
    üf
    -0.14
    .bc
    -0.14
    igram
    -0.14
    erald
    -0.13
    iosis
    -0.13
    aversal
    -0.13
    POSITIVE LOGITS
     race
    0.64
     races
    0.63
     Races
    0.55
     Race
    0.54
    Race
    0.53
    race
    0.51
    _race
    0.46
     ethnicity
    0.46
     ethnic
    0.43
     racial
    0.42
    Act Density 0.221%

    No Known Activations