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

    Neuronpedia

    INDEX
    Explanations

    sequences mentioning units of time, particularly "few" followed by a time measurement like weeks or months

    oai_token-act-pair · gpt-3.5-turbo

    the word "few" and related expressions indicating quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.87
    akings
    -0.79
    ilon
    -0.70
    agnar
    -0.68
    aban
    -0.68
    abal
    -0.67
    roup
    -0.66
    irst
    -0.66
    alam
    -0.65
    sein
    -0.64
    POSITIVE LOGITS
     dozen
    1.25
     hundred
    1.12
     thousand
    1.00
    een
    0.88
     weeks
    0.83
    dozen
    0.82
     minutes
    0.81
    ones
    0.80
     centimeters
    0.78
     nights
    0.77
    Act Density 0.039%

    No Known Activations