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

    Neuronpedia

    INDEX
    Explanations

    dates represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates and the specific format in which they are presented

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.72
    Reviewer
    -0.67
     retard
    -0.64
     diaper
    -0.64
     Bearing
    -0.64
     manual
    -0.62
     ESV
    -0.61
     transsexual
    -0.61
    puff
    -0.61
     ric
    -0.59
    POSITIVE LOGITS
    esville
    1.19
    itors
    1.18
    itor
    1.17
    vier
    1.15
    uary
    1.12
    eway
    1.05
    owitz
    0.97
    ice
    0.96
    omore
    0.92
    uine
    0.91
    Act Density 0.017%

    No Known Activations