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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to something being large or too good to be true

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express size or value judgments, particularly involving the terms "big" and "good"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tops
    -0.85
    ibrary
    -0.73
    atorium
    -0.71
    iversary
    -0.67
     guiActiveUn
    -0.66
    GH
    -0.64
    bers
    -0.63
    SO
    -0.62
    nect
    -0.61
    Services
    -0.61
    POSITIVE LOGITS
    idious
    0.68
    iated
    0.64
    aban
    0.62
    amas
    0.61
     cooks
    0.60
    yt
    0.60
    yz
    0.59
     too
    0.58
     agric
    0.58
     spoiled
    0.57
    Act Density 0.066%

    No Known Activations