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

    Neuronpedia

    INDEX
    Explanations

    negations within texts

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Not" as a way to introduce negation or contrast in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kamp
    -0.73
    stakes
    -0.72
    éĥ
    -0.72
    ãģ®ç
    -0.72
    ãģ«
    -0.71
    ç·
    -0.70
    creen
    -0.70
    ä¿
    -0.67
    velt
    -0.66
    è£
    -0.66
    POSITIVE LOGITS
    withstanding
    1.29
    orious
    1.15
    eworthy
    1.08
    epad
    1.07
    icably
    1.04
     necessarily
    1.03
    ifications
    0.92
    icing
    0.88
    ices
    0.88
    etheless
    0.87
    Act Density 0.073%

    No Known Activations