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

    Neuronpedia

    INDEX
    Explanations

    situations where the text is prompting the reader to continue reading

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating ongoing actions or options to continue reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.86
    axter
    -0.73
    »Ĵ
    -0.71
    rador
    -0.66
    ounty
    -0.65
    umin
    -0.63
    models
    -0.61
    gyn
    -0.61
    EStreamFrame
    -0.60
    bid
    -0.60
    POSITIVE LOGITS
     Continue
    0.75
     Reading
    0.69
     scrolling
    0.69
     Loading
    0.67
     CONTIN
    0.67
     reading
    0.65
     Advertisement
    0.65
     Continued
    0.62
     McConnell
    0.62
     Transcript
    0.61
    Act Density 0.013%

    No Known Activations