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

    Neuronpedia

    INDEX
    Explanations

    significant numerical values, particularly years and monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    777
    -0.15
    owe
    -0.14
    oga
    -0.14
    åŃĹå¹ķ
    -0.14
    ãĤ¦ãĥĪ
    -0.14
    uyên
    -0.13
     fame
    -0.13
    ·¸
    -0.13
     amb
    -0.13
    owell
    -0.13
    POSITIVE LOGITS
    å¹´
    0.25
    å¹´ãģ®
    0.20
     marks
    0.20
    ëħĦëıĦ
    0.20
     ëħĦ
    0.20
     yılı
    0.19
    ëħĦ
    0.19
    欧
    0.19
     saw
    0.19
    å¹´çļĦ
    0.18
    Act Density 0.085%

    No Known Activations