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

    Neuronpedia

    INDEX
    Explanations

    dates presented in a specific format, specifically with single-digit days or months followed by a two-digit year

    oai_token-act-pair · gpt-3.5-turbo

    dates and specific instances of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     careless
    -0.69
     prolifer
    -0.67
    tumblr
    -0.66
    ngth
    -0.65
    blogspot
    -0.64
     basket
    -0.63
     eaves
    -0.63
     cumbers
    -0.61
     noisy
    -0.60
     multiplying
    -0.59
    POSITIVE LOGITS
    âĸĪâĸĪ
    0.77
    eteenth
    0.76
     07
    0.74
     08
    0.72
     04
    0.72
    arcity
    0.71
    zona
    0.71
     06
    0.70
     09
    0.70
    rolet
    0.70
    Act Density 0.076%

    No Known Activations