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

    Neuronpedia

    INDEX
    Explanations

    instances where the term "few" is used in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a small number or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andise
    -0.75
    igation
    -0.74
    ESE
    -0.67
    nature
    -0.65
    venture
    -0.65
    atform
    -0.65
    webkit
    -0.64
    Reviewer
    -0.63
     Attribution
    -0.63
    abol
    -0.62
    POSITIVE LOGITS
     dozen
    1.58
     hundred
    1.57
     thousand
    1.44
     weeks
    1.23
     minutes
    1.20
     bucks
    1.18
     seconds
    1.14
     cents
    1.11
     months
    1.11
     moments
    1.10
    Act Density 0.079%

    No Known Activations