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

    Neuronpedia

    INDEX
    Explanations

    large quantities of something

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities, particularly the word "hundred"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.80
    akings
    -0.74
    minster
    -0.73
    akers
    -0.71
    Chart
    -0.70
    rang
    -0.66
    mort
    -0.66
    sectional
    -0.66
    Center
    -0.65
    aker
    -0.65
    POSITIVE LOGITS
     thousand
    1.23
     Thousand
    1.07
     ILCS
    1.00
     milliseconds
    0.98
    undred
    0.98
     hundred
    0.95
     miles
    0.92
    uously
    0.92
     000
    0.90
     watts
    0.90
    Act Density 0.006%

    No Known Activations