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

    Neuronpedia

    INDEX
    Explanations

    a phrase indicating that the article or story continues below

    oai_token-act-pair · gpt-3.5-turbo

    references to sections of articles or continued text indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceae
    -0.70
    umenthal
    -0.70
    ofi
    -0.67
    liest
    -0.65
    ĪĴ
    -0.62
    toe
    -0.61
    footed
    -0.61
    utic
    -0.60
    asters
    -0.59
    ogun
    -0.59
    POSITIVE LOGITS
     Below
    0.87
     Continued
    0.87
     Transcript
    0.79
     VIDEOS
    0.73
     Advertisement
    0.67
    },"
    0.67
     Loading
    0.66
     Provided
    0.65
     fmt
    0.64
     Continue
    0.64
    Act Density 0.008%

    No Known Activations