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

    Neuronpedia

    INDEX
    Explanations

    references to racial issues and disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĤãģ£ãģŁ
    -0.19
    ãģĤãĤĬ
    -0.19
    ãģĤãĤĭ
    -0.18
    oust
    -0.16
    Ùĩ
    -0.16
     rằng
    -0.16
    ãģĬ
    -0.15
     that
    -0.15
    371
    -0.14
     że
    -0.14
    POSITIVE LOGITS
    ched
    0.22
    麼
    0.21
    abouts
    0.20
    away
    0.19
    -ÑĤо
    0.19
    aways
    0.18
    cher
    0.18
    ching
    0.17
    chers
    0.17
    eway
    0.17
    Act Density 0.577%

    No Known Activations