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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases indicating a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    references to "some" and its varying contexts, implying a search for vague or nonspecific descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cycling
    -0.66
     yours
    -0.65
    uckle
    -0.62
     Clock
    -0.61
    ributes
    -0.61
    hips
    -0.59
    ades
    -0.58
    mers
    -0.58
    itten
    -0.57
    ourses
    -0.57
    POSITIVE LOGITS
    place
    1.40
    body
    1.38
    ones
    1.29
     sort
    1.28
     semblance
    1.21
     kind
    1.13
    ONE
    1.08
    how
    1.04
    THING
    0.92
     unspecified
    0.92
    Act Density 0.103%

    No Known Activations