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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "If you"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that directly address the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.71
    ãĥ³ãĤ¸
    -0.69
    BuyableInstoreAndOnline
    -0.67
    EStream
    -0.62
    catentry
    -0.61
    itol
    -0.61
    senal
    -0.60
    states
    -0.60
    assembly
    -0.59
    ļéĨĴ
    -0.58
    POSITIVE LOGITS
    're
    1.46
    've
    1.28
     wanna
    1.18
     want
    1.18
     haven
    1.16
     liked
    1.06
     weren
    1.04
     enjoyed
    1.04
     guessed
    1.04
    'd
    1.00
    Act Density 0.066%

    No Known Activations