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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format month/day/year with significant variation in date formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thous
    -0.72
    agna
    -0.72
     tremend
    -0.69
     fateful
    -0.68
     nomine
    -0.66
    iami
    -0.65
     practition
    -0.65
    paio
    -0.65
     Jobs
    -0.64
     bunny
    -0.63
    POSITIVE LOGITS
    88
    0.89
    657
    0.87
    708
    0.87
    665
    0.85
    806
    0.85
    008
    0.84
    307
    0.84
    245
    0.84
    66
    0.84
    646
    0.84
    Act Density 0.165%

    No Known Activations