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

    Neuronpedia

    INDEX
    Explanations

    dates or months mentioned in sentences

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and their significance in a timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.79
     constitu
    -0.74
    Interstitial
    -0.72
    speaking
    -0.69
     gifted
    -0.69
    desc
    -0.68
     Ital
    -0.67
    atem
    -0.66
     juggling
    -0.64
    mercial
    -0.63
    POSITIVE LOGITS
     2017
    0.91
     2015
    0.89
     2021
    0.88
    fair
    0.87
     2016
    0.85
    bug
    0.85
    onna
    0.84
     31
    0.83
     2019
    0.83
     29
    0.82
    Act Density 0.102%

    No Known Activations