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

    Neuronpedia

    INDEX
    Explanations

    explicit instances of societal issues, particularly those related to racism and misogyny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kli
    -0.15
    ostel
    -0.15
     Sunder
    -0.14
    ester
    -0.14
    INED
    -0.14
    YTE
    -0.14
    .library
    -0.14
    oft
    -0.14
     dispute
    -0.13
    .tbl
    -0.13
    POSITIVE LOGITS
    otch
    0.17
    plen
    0.15
    ì§ģ
    0.15
    779
    0.14
     explicitly
    0.14
    illow
    0.14
    MISS
    0.14
     Mills
    0.14
    ely
    0.13
    ılıç
    0.13
    Act Density 0.164%

    No Known Activations