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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in numerical day-month-year format

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and related temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CDC
    -0.69
    development
    -0.69
    IUM
    -0.66
    Sov
    -0.63
    PDATE
    -0.63
    utical
    -0.62
    opolis
    -0.62
    UTF
    -0.59
    anwhile
    -0.59
    BILITIES
    -0.58
    POSITIVE LOGITS
    tein
    0.68
    eve
    0.67
     onwards
    0.67
    å°Ĩ
    0.66
    oor
    0.64
     Revenge
    0.63
    tarians
    0.63
    ffe
    0.63
     Misty
    0.62
    endment
    0.62
    Act Density 0.165%

    No Known Activations