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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "Month day"

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and references to the month of January

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bearing
    -0.68
    puff
    -0.68
     manual
    -0.66
    ropolitan
    -0.65
    Reviewer
    -0.65
    cular
    -0.64
     diaper
    -0.63
     Flavoring
    -0.62
     diapers
    -0.61
    LLOW
    -0.61
    POSITIVE LOGITS
    uary
    1.15
    itor
    1.11
    vier
    1.05
    itors
    1.02
    ice
    0.90
    esville
    0.89
    owitz
    0.89
    ocide
    0.88
    eway
    0.86
    ibel
    0.86
    Act Density 0.011%

    No Known Activations