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

    Neuronpedia

    INDEX
    Explanations

    dates or specific days mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days or events, particularly those related to holidays and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailable
    -0.72
    uv
    -0.70
    ometric
    -0.70
     Roose
    -0.68
    cro
    -0.66
    abolic
    -0.65
     phosphorus
    -0.65
    APTER
    -0.63
    iological
    -0.61
    Magn
    -0.59
    POSITIVE LOGITS
     2019
    1.09
     2017
    1.08
     2018
    1.04
     festivities
    1.04
     2015
    1.00
     2016
    0.99
     2014
    0.95
     2013
    0.95
     weekend
    0.94
    eve
    0.87
    Act Density 0.133%

    No Known Activations