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

    Neuronpedia

    INDEX
    Explanations

    words indicating conditions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aggio
    -0.15
    ugu
    -0.15
    aga
    -0.14
    ÙĬÙĨÙĬ
    -0.14
    ãģĿ
    -0.14
    (suite
    -0.14
    ¹
    -0.14
    bai
    -0.14
    owie
    -0.13
    quared
    -0.13
    POSITIVE LOGITS
    å¹¹ç·ļ
    0.16
    ÙĪÛĮس
    0.15
    313
    0.15
     Morav
    0.15
    اص
    0.15
    elters
    0.15
    amento
    0.15
    erno
    0.15
    SA
    0.15
     Mobil
    0.14
    Act Density 0.000%

    No Known Activations