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

    Neuronpedia

    INDEX
    Explanations

    comparisons or statistical information

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "pale."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frames
    -0.72
    ORGE
    -0.71
    ATTLE
    -0.70
    mingham
    -0.66
    ÄŁ
    -0.66
    è¦ļéĨĴ
    -0.65
    ALLY
    -0.64
     srfAttach
    -0.63
    enegger
    -0.62
    schild
    -0.61
    POSITIVE LOGITS
    umatic
    0.97
    haps
    0.97
    ciation
    0.79
    uma
    0.76
    formance
    0.75
    aic
    0.73
     nipples
    0.72
    adium
    0.72
    otal
    0.71
    etary
    0.70
    Act Density 0.070%

    No Known Activations