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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating setting something aside or disregarding it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "set aside."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coefficients
    -0.63
    eway
    -0.62
    cat
    -0.62
     Zeit
    -0.62
    è¦ļéĨĴ
    -0.62
    oc
    -0.60
    hab
    -0.60
     chase
    -0.60
    ammed
    -0.59
    cel
    -0.58
    POSITIVE LOGITS
     aside
    1.24
    heid
    0.96
    Enjoy
    0.69
    Congratulations
    0.69
    MENTS
    0.67
    comings
    0.66
     onlook
    0.64
    Artist
    0.63
     notwithstanding
    0.63
    epad
    0.62
    Act Density 0.009%

    No Known Activations