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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "as" indicating comparisons or references in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ever
    -0.17
    ãĤªãĥª
    -0.16
    464
    -0.15
    eyi
    -0.14
    sted
    -0.14
    ecc
    -0.14
    eker
    -0.14
    ollen
    -0.14
    ivec
    -0.14
    orem
    -0.14
    POSITIVE LOGITS
     per
    0.19
     compared
    0.17
    uth
    0.17
    iba
    0.15
    Ä
    0.15
    elsen
    0.15
    Ti
    0.14
    anas
    0.14
    oka
    0.14
     Nolan
    0.14
    Act Density 0.089%

    No Known Activations