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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cy
    -0.75
    o
    -0.67
    ys
    -0.66
    ته
    -0.66
     Baton
    -0.64
    ded
    -0.64
    ことはない
    -0.63
     Hov
    -0.62
    ed
    -0.62
    e
    -0.62
    POSITIVE LOGITS
     WHICH
    1.47
     which
    1.41
     Which
    1.37
    which
    1.35
    Which
    1.27
    Datuak
    1.26
     wich
    1.14
    hich
    1.06
    ซึ่ง
    1.06
    ]**
    1.04
    Act Density 0.166%

    No Known Activations