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

    Neuronpedia

    INDEX
    Explanations

    phrases related to valuable items or possessions

    oai_token-act-pair · gpt-3.5-turbo

    references to value or valuables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olitan
    -0.79
    pread
    -0.72
    hower
    -0.69
    liness
    -0.69
    soever
    -0.66
    sein
    -0.65
     Bread
    -0.65
     Daylight
    -0.63
     EntityItem
    -0.63
    éĹĺ
    -0.63
    POSITIVE LOGITS
    ueless
    1.06
    uations
    1.05
    ibr
    0.99
    entin
    0.90
    uing
    0.88
    ipers
    0.86
    anche
    0.85
    ign
    0.85
    enture
    0.84
    uably
    0.84
    Act Density 0.008%

    No Known Activations