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

    Neuronpedia

    INDEX
    Explanations

    dates and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of temporal expressions and structured data, such as dates and routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.92
    vre
    -0.66
     paws
    -0.65
     blaster
    -0.65
    .}
    -0.65
    ilogy
    -0.61
    BRE
    -0.61
    eyes
    -0.60
     absor
    -0.59
    ims
    -0.59
    POSITIVE LOGITS
     June
    1.80
     October
    1.78
     July
    1.77
     September
    1.77
     February
    1.77
     April
    1.75
     December
    1.74
     November
    1.74
     January
    1.72
     August
    1.72
    Act Density 0.067%

    No Known Activations