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

    Neuronpedia

    INDEX
    Explanations

    the word "some" and variations of its use in phrases indicating quantity or selection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somehow
    -0.20
    las
    -0.18
    åIJĦç§į
    -0.16
    swer
    -0.16
    ãĥªãĥ¼ãĤº
    -0.16
    walker
    -0.15
     respectively
    -0.15
    tings
    -0.15
    اÙĨÙĩ
    -0.15
    ä½ķãģĭ
    -0.15
    POSITIVE LOGITS
    ones
    0.38
    place
    0.36
    /all
    0.34
    hw
    0.32
    -times
    0.27
     of
    0.25
    ONE
    0.24
    ht
    0.24
    how
    0.23
    body
    0.23
    Act Density 0.121%

    No Known Activations