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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "wholeness" or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ARIA
    -0.45
     Epson
    -0.41
     adipo
    -0.41
     epson
    -0.40
     merci
    -0.40
     SDC
    -0.40
     Aria
    -0.39
     Gatwick
    -0.38
     Dac
    -0.38
     Lymp
    -0.38
    POSITIVE LOGITS
     whole
    2.02
    whole
    1.97
    Whole
    1.81
     WHOLE
    1.72
     Whole
    1.69
     entire
    1.64
    entire
    1.45
     Entire
    1.43
    Entire
    1.38
     ganze
    1.31
    Act Density 0.143%

    No Known Activations