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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving large quantities or sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anh
    -0.15
    assi
    -0.15
    ocker
    -0.14
     ë°Ģ
    -0.14
    avir
    -0.14
    jong
    -0.14
     Blanch
    -0.13
    /vnd
    -0.13
    (åľŁ
    -0.13
    arra
    -0.13
    POSITIVE LOGITS
     entire
    0.28
     Entire
    0.22
     whole
    0.20
    anta
    0.20
     entirety
    0.18
     toÃłn
    0.18
    whole
    0.18
    æķ´ä¸ª
    0.17
    aeda
    0.17
    617
    0.17
    Act Density 0.062%

    No Known Activations