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

    Neuronpedia

    INDEX
    Explanations

    words related to covers, lids, and hinges

    oai_token-act-pair · gpt-3.5-turbo

    references to lids and their characteristics or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortune
    -0.71
    bidden
    -0.69
    Ĥª
    -0.69
     Borough
    -0.68
    WER
    -0.68
     Blessed
    -0.66
    gotten
    -0.66
     Samoa
    -0.66
     Bread
    -0.66
     Capital
    -0.65
    POSITIVE LOGITS
     lid
    1.20
    stones
    0.93
    ysis
    0.92
    wcs
    0.87
    wheel
    0.86
    heed
    0.84
    bell
    0.82
    stone
    0.81
    pit
    0.78
    coin
    0.76
    Act Density 0.008%

    No Known Activations