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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or frequency

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "each."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cu
    -0.72
    etics
    -0.70
    Bs
    -0.64
    keepers
    -0.64
     Roberts
    -0.62
    Jer
    -0.60
    keeper
    -0.60
     Journalism
    -0.58
     contradictions
    -0.57
    YC
    -0.57
    POSITIVE LOGITS
     month
    1.06
     week
    1.00
     weekday
    0.96
     year
    0.91
     successive
    0.84
     morning
    0.83
     day
    0.82
     fortnight
    0.81
    "}],"
    0.80
     hemisphere
    0.80
    Act Density 0.036%

    No Known Activations