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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "shift" in different forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lau
    -0.56
    ieros
    -0.56
    Macau
    -0.56
    )]=
    -0.55
     Maryland
    -0.55
     gluon
    -0.55
     стра
    -0.54
    }{||
    -0.54
    execu
    -0.54
    </h1>
    -0.53
    POSITIVE LOGITS
     shift
    3.71
     shifts
    3.40
     Shift
    3.33
    shift
    3.33
    Shift
    3.09
     Shifts
    3.07
     SHIFT
    3.00
    shifts
    2.91
     shifted
    2.86
    hift
    2.81
    Act Density 0.086%

    No Known Activations