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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "respective."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kah
    -0.16
    sworth
    -0.15
    sburg
    -0.15
    spam
    -0.15
    180
    -0.14
    relude
    -0.14
    illon
    -0.14
     Chung
    -0.14
    bour
    -0.14
    erd
    -0.14
    POSITIVE LOGITS
    dera
    0.17
     çek
    0.14
    oupper
    0.14
    itom
    0.14
    olum
    0.14
    ики
    0.14
    Та
    0.14
    eker
    0.14
    uge
    0.13
    /Foundation
    0.13
    Act Density 0.007%

    No Known Activations