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

    Neuronpedia

    INDEX
    Explanations

    references to historical oppression and racial inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     libertin
    -0.19
    efs
    -0.15
     Vik
    -0.14
    ç¾Ĭ
    -0.14
    ãĥ©ãĤ¤ãĥ³
    -0.14
    hani
    -0.13
    ëĤ
    -0.13
     {{{
    -0.13
     tribunal
    -0.13
     Chap
    -0.13
    POSITIVE LOGITS
     segregation
    0.34
     segregated
    0.30
     Jim
    0.29
    Jim
    0.27
     whites
    0.25
     Seg
    0.24
     segreg
    0.24
     jim
    0.23
     seg
    0.23
     Southern
    0.23
    Act Density 0.206%

    No Known Activations