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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location or historical figure, particularly related to Denver

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ver" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erva
    -0.70
    ollo
    -0.67
    akings
    -0.66
    uana
    -0.65
    ental
    -0.64
    ENDED
    -0.63
    »Ĵ
    -0.62
    ĪĴ
    -0.61
    ourt
    -0.61
    ixed
    -0.61
    POSITIVE LOGITS
    dict
    1.09
    theless
    1.07
    gence
    1.05
    deen
    1.01
    ver
    0.95
    tex
    0.95
    ding
    0.88
    ging
    0.86
    gent
    0.83
    izable
    0.82
    Act Density 0.012%

    No Known Activations