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

    Neuronpedia

    INDEX
    Explanations

    references to watchmaking and its intricate details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kumar
    -0.14
     buflen
    -0.14
     tow
    -0.14
    sert
    -0.14
    tener
    -0.14
    adır
    -0.14
    coli
    -0.14
    маг
    -0.14
     Holden
    -0.13
     Äijạo
    -0.13
    POSITIVE LOGITS
     complication
    0.23
     complications
    0.22
     Skeleton
    0.21
     skeleton
    0.21
     Manufact
    0.20
    GMT
    0.19
     TOUR
    0.19
     Tour
    0.19
     tour
    0.19
     chron
    0.18
    Act Density 0.015%

    No Known Activations