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

    Neuronpedia

    INDEX
    Explanations

    a specific sequence of characters, "amp", often found in URLs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "amp"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.82
    BLIC
    -0.79
    ĪĴ
    -0.76
    ignty
    -0.72
    ationally
    -0.65
    ģĸ
    -0.64
    ALLY
    -0.64
    chard
    -0.63
    ryu
    -0.63
    ordan
    -0.63
    POSITIVE LOGITS
    shire
    1.09
    aign
    1.00
    hetamine
    0.96
    eters
    0.94
    agne
    0.94
    aic
    0.91
    oline
    0.85
    oons
    0.85
    ocalypse
    0.83
    owered
    0.80
    Act Density 0.023%

    No Known Activations