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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a small quantity or number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "few"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.80
    yrinth
    -0.74
    leneck
    -0.72
    alam
    -0.71
     agre
    -0.70
    roit
    -0.70
     conclud
    -0.69
    andise
    -0.67
    webkit
    -0.65
    akings
    -0.65
    POSITIVE LOGITS
     dozen
    1.47
     hundred
    1.43
     thousand
    1.26
     weeks
    1.18
     months
    1.07
    dozen
    1.06
     days
    1.05
     minutes
    1.04
     nights
    0.97
     moments
    0.94
    Act Density 0.055%

    No Known Activations