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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating a relatively small quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "few."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agre
    -0.76
    acus
    -0.76
    andise
    -0.74
    venture
    -0.72
     destro
    -0.72
    yrinth
    -0.71
     conclud
    -0.71
    igation
    -0.70
    iquette
    -0.69
    vertisement
    -0.68
    POSITIVE LOGITS
     hundred
    1.52
     dozen
    1.51
     thousand
    1.34
     weeks
    1.25
     minutes
    1.13
     days
    1.12
     months
    1.11
     moments
    1.09
     seconds
    1.04
     hours
    1.04
    Act Density 0.074%

    No Known Activations