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

    Neuronpedia

    INDEX
    Explanations

    references to pockets or small storage spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strict
    -0.20
    hu
    -0.17
     lượt
    -0.16
    ?option
    -0.15
    jak
    -0.15
    yah
    -0.15
    ugins
    -0.15
    oeff
    -0.14
    hir
    -0.14
    hma
    -0.14
    POSITIVE LOGITS
    ed
    0.30
    knife
    0.29
    -sized
    0.27
    eer
    0.25
    book
    0.25
    ing
    0.24
     sized
    0.23
    -size
    0.23
    ful
    0.23
    ting
    0.22
    Act Density 0.019%

    No Known Activations