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

    Neuronpedia

    INDEX
    Explanations

    dates or specific days

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates in February

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.76
    éĹĺ
    -0.69
    enegger
    -0.64
    schild
    -0.63
    ÃįÃį
    -0.61
    Offline
    -0.60
     Regulatory
    -0.58
     parap
    -0.58
     polish
    -0.58
     Tune
    -0.58
    POSITIVE LOGITS
    uary
    1.09
    ice
    1.04
    nd
    0.98
    ruary
    0.94
    iors
    0.91
    omore
    0.91
    isco
    0.91
    vier
    0.91
    oreal
    0.89
    ument
    0.89
    Act Density 0.005%

    No Known Activations