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

    Neuronpedia

    INDEX
    Explanations

    dates or months mentioned in texts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bidder
    -0.67
     chops
    -0.66
     continu
    -0.63
     looph
    -0.60
     voc
    -0.59
     subscript
    -0.58
     Shed
    -0.58
     subcontract
    -0.58
     stead
    -0.57
     phr
    -0.57
    POSITIVE LOGITS
    culus
    0.91
    ibe
    0.78
    -'
    0.70
    iatus
    0.70
    quickShipAvailable
    0.68
    iren
    0.64
    enium
    0.64
    ame
    0.64
    Bern
    0.63
    Lay
    0.62
    Act Density 0.129%

    No Known Activations