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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" followed by numerical dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plin
    -0.77
    rors
    -0.74
    pee
    -0.69
    pees
    -0.66
    fters
    -0.65
    rament
    -0.63
    pots
    -0.63
    perse
    -0.62
    otle
    -0.61
    inis
    -0.61
    POSITIVE LOGITS
     behalf
    1.52
     July
    1.46
     September
    1.45
     June
    1.42
     April
    1.42
     October
    1.41
     December
    1.41
     January
    1.40
     February
    1.40
     August
    1.40
    Act Density 0.160%

    No Known Activations