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

    Neuronpedia

    INDEX
    Explanations

    elements related to legal accusations and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bette
    -0.17
    еÑĤÑĮÑģÑı
    -0.15
    rema
    -0.15
    deniz
    -0.15
    ķĮ
    -0.15
    å·Ŀ
    -0.14
    ä¹İ
    -0.14
    ecko
    -0.14
    нож
    -0.14
    lest
    -0.14
    POSITIVE LOGITS
     too
    0.27
    too
    0.24
    -too
    0.23
    Too
    0.21
    太
    0.20
     Too
    0.19
     TOO
    0.19
     bias
    0.18
     should
    0.18
     Should
    0.18
    Act Density 0.190%

    No Known Activations